DE112017001229T5 - BROWSING INTERFACE FOR ARTICLE MATCHES WITH DIFFERENT MEASURES AND LENGTHS - Google Patents

Abstract

Features are provided for an interface for browsing images of articles of different scales and lengths, such as: As clothing disclosed. The interface can present two parts of a subject, with each part selected from different image datastores. The interface can provide a consistent view of the parts. For example, a first part may be taken from an image of the subject wearing a golf shirt and long pants. A second part can be taken from a picture of the subject in a long-sleeved shirt and shorts. The first part can only show the golf shirt and the second part can only show the shorts, providing a representation of what the subject would look like when the shirt shown in the first picture wore the shorts shown in the second image.

Description

BACKGROUND

An imaging system can be used to capture images of a user over several days. The captured images may include various items (eg, clothing, accessories, shoes, etc.). A user interface presented on a display of an electronic device may be provided to allow the user to browse the images showing the outfits or looks worn by the user over a period of time. This may help in the selection of favorite outfits that have been worn frequently, or in identifying items that have rarely been worn to remove them from the user's closet.

Retailers, retailers, vendors, manufacturers, stylists, designers, and others may provide or promote such user interfaces to allow a user to browse articles in an electronic catalog and / or to search an electronic catalog for items to purchase or otherwise purchase Are available. For example, the user may scroll through a grid or list of articles. These items are typically shown in pictures taken while worn by a model or on a hanger, but not by the user browsing.

list of figures

• 1A ist ein bildliches Diagramm, das eine beispielhafte Benutzerschnittstelle veranschaulicht, die zumindest teilweise von einem Browsing-Dienst erzeugt wurde, wobei die Benutzerschnittstelle einen interaktiven Browsing-Bereich mit einem ersten Artikel beinhaltet.
• 1B ist ein bildliches Diagramm, das die beispielhafte Benutzerschnittstelle von 1A mit einer aktivierten Browsing-Steuerung veranschaulicht.
• 1C ist ein bildliches Diagramm, das die beispielhafte Benutzerschnittstelle von 1A nach der Aktivierung einer Browsing-Steuerung veranschaulicht.
• 2 ist ein Blockdiagramm, das eine veranschaulichende Betriebsumgebung zeigt, in der ein Zugriffsgerät, das einen Browsing-Dienst bereitstellt, es dem Benutzer ermöglicht, das Katalogsystem über Benutzerschnittstellen, wie die in 1A, 1B und 1C dargestellten, zu browsen.
• 3 stellt eine allgemeine Architektur eines beispielhaften Zugriffsgeräts dar, das einen Browsing-Service für das effiziente und interaktive Browsen von Artikeln und/oder Bildern bereitstellt, die von dem Katalogsystem verwaltet werden, das in 2 gezeigt ist.
• 4 ist ein Flussdiagramm, das ein im Katalogsystem implementiertes beispielhaftes Verfahren zum Browsen von Artikelbildern darstellt.
• 5A ist ein bildliches Diagramm eines illustrativen Strukturmodells für ein Subjekt, das in einem Bild erscheint.
• 5B ist ein bildliches Diagramm des Bildes, in dem das Subjekt erscheint, das mit dem Strukturmodell von 5A abgebildet ist.
• 5C zeigt einen Teil des Bildes, das in 5B segmentiert gezeigt wird, um den Teil des Bildes zu zeigen, der dem Rumpf und dem Kopf des Subjekts entspricht.
• 5D zeigt einen Teil des Bildes, das in 5B segmentiert gezeigt wird, um den Teil des Bildes zu zeigen, der den Beinen des Subjekts entspricht.
• 6A stellt ein veranschaulichendes Verhältnismodell zur Segmentierung dar.
• 6B stellt eine Bildeingabe zur Segmentierung unter Verwendung des Verhältnismodells von 6A dar.
• 6C stellt ein normalisiertes Bild dar, das mit dem Verhältnismodell von 6A erzeugt wurde.
• 6D zeigt einen Teil des segmentierten Bildes, um den Teil des Bildes zu zeigen, der dem Rumpf des Subjekts entspricht.
• 7 ist ein Flussdiagramm, das ein im Browsing-Dienst implementiertes beispielhaftes Verfahren darstellt.
• 8A bis 8D stellen die Segmentierung von zwei Bildern und Ausrichtung von segmentierten Teilen aus den zwei Bildern gemäß dem in 7 gezeigten Verfahren dar.

Embodiments of various inventive features will now be described with reference to the following drawings. In all drawings, reference numerals may be reused to indicate the correspondence between the mentioned elements. The drawings are provided to illustrate the example embodiments described herein and are not intended to limit the scope of the disclosure.

• 1A Figure 4 is a pictorial diagram illustrating an exemplary user interface generated, at least in part, by a browsing service, wherein the user interface includes an interactive browsing area with a first article.
• 1B is a pictorial diagram illustrating the exemplary user interface of 1A with an enabled browsing control.
• 1C is a pictorial diagram illustrating the exemplary user interface of 1A after enabling a browsing control.
• 2 FIG. 4 is a block diagram illustrating an illustrative operating environment in which an access device providing a browsing service enables the user to access the catalog system via user interfaces such as those described in FIG 1A . 1B and 1C shown to browse.
• 3 FIG. 4 illustrates a general architecture of an exemplary access device providing a browsing service for efficiently and interactively browsing articles and / or images managed by the catalog system incorporated in 2 is shown.
• 4 Figure 13 is a flow chart illustrating an exemplary method of browsing article images implemented in the catalog system.
• 5A Figure 11 is a pictorial diagram of an illustrative structural model for a subject appearing in an image.
• 5B is a pictorial diagram of the picture in which the subject appears, which corresponds to the structural model of 5A is shown.
• 5C shows a part of the image that is in 5B segmented to show the part of the image that corresponds to the subject's torso and head.
• 5D shows a part of the image that is in 5B segmented to show the part of the image corresponding to the subject's legs.
• 6A represents an illustrative ratio model for segmentation.
• 6B provides an image input for segmentation using the ratio model of 6A represents.
• 6C represents a normalized image consistent with the relationship model of 6A was generated.
• 6D shows a portion of the segmented image to show the portion of the image that corresponds to the subject's torso.
• 7 Figure 5 is a flowchart illustrating an example method implemented in the browsing service.
• 8A to 8D represent the segmentation of two images and alignment of segmented parts from the two images according to the in 7 shown method.

DETAILED DESCRIPTION

With the advent of digital imaging and the proliferation of imaging systems, the number of digitally detected images is decreasing further to. A common type of image is a "selfie" or self-portrait image of a subject. The self-portraits are typically taken from a similar location (eg, one arm's length away) of the subject. The images can be stored locally on the image capture system or remotely in a networked data store. The image capture system may be used as a standalone device or with or in another access device such as a television, a set-top box, a mobile phone, a mirror, a door, a window, a dashboard, a home appliance, a videoconferencing system, or the like. An example of an image capturing system is presented in the Dec. 11, 2015 filed U.S. Patent Application No. 14/967086 which is common property and is incorporated herein in its entirety.

Individually, the images captured by the imaging system can be searched to identify different looks of the subject over time. In the following, unique features will be described which make it possible to combine these different images so that a part of a first image of a subject can be viewed with a part of a second image of the subject. For example, a first part may be taken from an image of the subject wearing a golf shirt and long pants. A second part can be taken from a picture of the same subject in a long-sleeved shirt and shorts. The first part can only show the golf shirt and the second part can only show the shorts, providing a representation of what the subject would look like when wearing the shirt shown in the first picture with the shorts shown in the second picture. The interface represents two parts of a subject, each part being selected from different data memories of images. The interface can provide a consistent view of the parts. This provides a new way to search a collection of images to identify new combinations of articles to be matched.

In one aspect, a user interface for presenting parts of two different images is described. In addition to displaying the images on the user interface, other aspects are described to improve the display of the parts so that the display presents the subject as the wearer of an outfit for which no image exists. A browsing service may be provided to coordinate the user interface and image processing for displaying images therein.

Examples of image processing implemented by the browsing service include automatic segmentation and alignment of images for display via an interface. The pictures can have different scales and lengths. The items shown in the pictures, such as. As clothes, therefore, may not be presented uniformly. Segmentation of the images into image parts in which an image part shows a specific article is described. The segmentation may be done using models and / or complex image analysis, as described below. To obtain a realistic view of the subject when displaying image segments together on an interface, additional alignment of the image segments may be performed. The alignment can be done using models and / or complex image analysis, as described below.

Although various embodiments are described with reference to subjects and articles such as clothing, it is believed that the described systems, methods, and devices are for other subjects (e.g., non-human subjects) such as home furnishings, clothing, garments, vehicles, or mechanical devices and / or other items shown in the pictures (eg, lamps, carpets, chairs, tables, sofas, floor mats, steering wheels, rims, tires, door panels, hinges, covers, keyboards, housings, etc.). As used herein, the term "article" is used not only for the ordinary meaning but also for the designation of an article itself (e.g., a particular product) and for its description or presentation in a computer system or electronic catalog. As can be seen from the context in which it is used, the term here sometimes refers only to the object itself or only to its representation in the computer system.

1A Figure 4 is a pictorial diagram illustrating an exemplary user interface generated, at least in part, by a browsing service, wherein the user interface includes an interactive browsing area with a first article. The browsing service can work on an access device with the user interface 100 be implemented. In some implementations, the browsing service may be implemented on a catalog system in communication with an access device. In some implementations, the browsing service may be implemented as a distributed service, with some functions implemented on the access device and some functions on a catalog system. In a distributed configuration, it may be desirable to provide similar functions to both the access device and the catalog system to enable dynamic allocation of processing between the access device and the catalog system. For example, if the access device has limited resources (eg, power, bandwidth, data storage, Communication channel, etc.), it may be desirable to assign the processing to the catalog system until the resources for the access device are increased.

The user interface 100 includes an interactive image viewer 102 , The in 1A shown interactive image viewer 102 is configured to represent two image zones, an upper display zone 104 and a lower display zone 106 , A partition 108 separates the upper display zone 104 and the lower display zone 106 , Additional display zones can be provided with corresponding partitions. As a non-limiting example, three display zones with two partitions can be inserted between the respective display zones. Depending on the implementation, the display zones may be the same size or different sizes. The partition 108 is represented as a horizontal partition. In some implementations, additional or alternative partitions may be included. For example, a vertical subdivision may be used to subdivide an interior interactive image viewer, with a first zone for the display of an end table and another zone for the display of a couch. The partition 108 may be associated with partition information that indicates where the partition is 108 in terms of the interactive image viewer 102 located.

Each zone can display part of an image. As in 1A shown, shows the upper display zone 104 a first part 140 an image with a subject. The first part 140 of the picture, which uses the example of 1A shows, shows the head and torso of a person. The lower display zone 106 shows a second part 144 a picture that shows the subject. The second part 144 of the subject in the example of 1A shows the legs and feet of the person.

The first part 140 and the second part 144 can be taken from two different pictures. The images can be accessed on the access device with the user interface 100 be stored, for. B. in the internal memory of a smartphone. When loading the user interface for the first time 100 You can select two images from a datastore that are in the zones of the interactive image viewer 102 being represented. The selection may be based on the date (eg, selection of images that are more than a predetermined number of days ago), prior preference information for images (eg, images associated with more views than less frequently viewed images preferred), randomization, color of an article shown in the picture, category of an article shown in the picture (eg top, evening wear, shirt, skirt, pants, shorts, etc.) or a combination thereof. In some implementations, the selection may also rely on information that is detected or otherwise provided by the access device. For example, the access device may be with the user interface 100 determine the temperature or season. If the access device has determined that the temperature is hot, it may be better to display warm-weather clothing than ski clothing. As another example, the access device may include a calendar that stores event information. The event information may indicate when and / or what type of event the user might attend. When accessing the user interface 100 Event information from the browsing service can be used at the time of the event to select images for display. For example, if the event is titled "Business Meeting with James", the pictures showing professional clothing may be selected. However, if the event is titled "Dancing With Friends", casual or club clothing may be preferred during the selection process.

In some implementations, one or more of the images may be selected from a remote image data store. For example, if the access device is using the UI 100 connected to a network, the user of the access device can store images in a networked location, e.g. On a photo sharing website, social media site, or other networked data storage service. In such implementations, selection of an image from the remote image data store may continue based on network connectivity, availability of the remote data store of images, resources available to the access device (eg, when operating in power save mode or via a network connection with low bandwidth, avoiding selection from the remote source to conserve resources) or a combination thereof.

The data storage of the images need not be under the control of or owned by the user. For example, the user interface 100 be configured to connect to a third-party image data store, such as a friend or family member. In such implementations, the images of articles that the third-party user wears may be through the user interface 100 be searched. This can provide the advantage that the user can find a garment that he can borrow from the third party to complete an outfit.

In some implementations, the user interface may be 100 Obtain images from a catalog system. In such implementations can an image of an article available for purchase or other purchase (leasing, lending, donation, etc.) and selected in the interactive image viewer 102 be recorded. The presentation of such images may be useful to guide the user to new or alternative articles that he wishes to purchase by displaying them in association with an article already in the user's possession. For example, the first part 140 show the user in her favorite red blouse while the second part 144 shows an image from a catalog system of a popular (for example, among the users of the catalog system) pair of white shorts. In some implementations, it may be desirable to provide a visual artifact for images contained in a catalog system. For example, the white shorts may be displayed in a distinctive color that outlines the article as shown in the picture. This frame can be color-coded to that in the user interface 100 to visually associate displayed items with the catalog system offering the item. In such implementations, multiple catalog systems can be configured as image data sources. By using unique hints, the user interface can 100 quickly represent the source of a particular article image. Other examples of visual artifacts that may be included as an alternative or in addition to another visual artifact are: a visible highlight, a symbol, letters, numbers, hue, or color filters. In some implementations, images that display articles from a catalog system may be further referenced by non-visual cues such as sound or vibration (eg, haptic feedback).

As in 1A shown, the user interface 100 include one or more controls (eg, buttons, clickable images, hyperlinks). A control can be activated (eg, clicked, selected, tapped, verbally identified, etc.) to send a message to the browsing service that represents the user interface 100 coordinated. An example of such a controller is a "buy look" button 124. Upon activation of the "buy look" button 124, the user may interface to purchase one or more items displayed in the interactive display area (eg, interactive image viewer 102 ), which can be provided by a catalog system. Activation may cause the browsing service to send information to the catalog system. The transmitted information can identify the items shown in the images supplied by the catalog system. This information can be used by the catalog system and / or the browsing service to initiate the purchase. In some implementations, information about the user may also be provided to the catalog system. For example, the user may be associated with an account number within the catalog system. When the "buy-buy" button 124 is activated, this account number can be transmitted to the catalog system to facilitate the retrieval of user information required to complete the transaction for an article.

Browsing controls are also in 1A shown. The browsing controls may be associated with a display zone. For example, browsing control 110 and browsing control 112 with the upper display zone 104 Associated while browsing control 114 and browsing control 116 with the lower display zone 104 are associated. When a browsing control is enabled, the browsing control will cause the image data displayed in the associated display zone to change. In some implementations, the change may include animated motions for the image data in the direction indicated. If z. B. the browsing control 110 is activated, this will be in the upper display zone 104 displayed image from the upper display zone 104 scrolled and replaced with a new image.

Because portions of images are displayed in display zones, it may be desirable to align the portions to provide a realistic, continuous view of the subject. The segmentation and / or alignment of the images can be performed by the browsing service to view the parts of the images that are above the interactive image viewer 102 be displayed automatically. In some implementations, the interactive image viewer may 102 also get specific settings for a display zone. For example, the user may be the first part 140 within the upper display zone 104 pull to the first part 140 closer to the second part 144 the lower display zone 106 align. This setting can be saved by the browsing service and used in the presentation and / or orientation of future image parts. The segmentation and alignment features are described in more detail below.

1B is a pictorial diagram illustrating the exemplary user interface of 1A with an enabled browsing control. An activated browsing control 130 is in 1B shown. Upon activation, the first part becomes 140 of the subject in one direction 132 moved with the enabled browsing control 130 is associated. In 1B is the direction 132 to the left of the user interface 100 , If the first part 140 is moved to the left, is in the upper display zone 104 a spare part 143 displayed. In some implementations, the rates are around the the first part 140 is moved and a third part 142 is displayed, the same.

1C is a pictorial diagram illustrating the exemplary user interface of 1A after enabling a browsing control. The browsing control 110 is shown in the non-activated form, similar to the browsing control 110 in 1A appears. The interactive image viewer 102 now shows the spare part, the third part 142 , from a first image in the upper display zone 104 with the second part 144 from an image other than the first image in the lower display zone 106 , As shown, the interactive image viewer presents 102 provide a complete view of the subject using image data from two different images. In some implementations, the user may view the images with the interactive image viewer 102 browse to discover new combinations of looks. This allows the user interface 100 represent hypothetical looks for the user for whom there is not a single image in an image source.

While the user is the interactive image viewer 102 can be displayed, a combination of image parts that the user wants to save. A "save-look" button 122 can in the user interface 100 includes his. After activation, the "save look" button 122 Submit information to the browsing service that indicates the current status of the interactive image viewer 102 Show. The current status information, when provided to the browsing service, includes the information for the browsing service to the user interface 100 at the time of activation of the "save look" button 122 restore. The current status information may include one or more of the following: identifier of the images shown, sources of the images shown, the location of the partition 108 or the position of the image parts within a display zone. The current status information can be saved using a session log. The session record may be associated with a record identifier. Using the record identifier, the browsing service can retrieve the session record and the user interface 100 in their state at the time of activation of the "save look" button 122 reset to default.

The user interface 100 may include additional controls that, when activated, the status of the interactive image viewer 102 and / or the user interface 100 to change. In the examples in 1A . 1B and 1C can be an upper control panel 120a with the upper display zone 104 and a lower control panel 120b with the lower display zone 106 be associated. In such implementations, activation of a controller within the control panel means activation for the associated display zone. If z. B. via the lower panel 120b A "more info" control enabled via the user interface 100 more information on the one in the lower display zone 106 shown image part can be retrieved and presented. The image was taken from a local image store (for example, datastore of the access device that is the user interface 100 presented), the additional information may include metadata for the image, such as: For example, the recording time of the image or the location where the image was taken. If the image has been retrieved from a catalog system, the additional information may e.g. For example, an identifier of the catalog system, details of an article displayed in the image, such as available sizes, colors or patterns, pricing information for an article displayed in the image, user ratings of an article displayed in the image, textual information about an article displayed in the image, or the availability of an article ( eg in stock in a local store, available on order within a certain period of time).

Another exemplary control, in the upper control panel 120a or in the lower panel 120b can be included is a "My Looks Search" control. The "My Looks Search" control can trigger a search for pictures of the user. Activation of the "My Looks Search" control may also include a search with search criteria taken from the image or part of the corresponding zone. For example, enabling the "My Looks Search" control in the top panel 120a for the in 1C shown user interface 100 to trigger a search for images that the user with a similar article as in the upper display zone 104 show (eg a top or a striped top). In some implementations, the user interface may be 100 also display a criteria entry control upon activation of the "Find My Looks" control. The criteria entry control may be configured to receive values to further narrow the search, e.g. For example, by date, color, item type (eg category) or other criteria.

After running the search, the search results can be accessed through the user interface 100 to be provided. One way to provide the search results is the interactive image viewer 102 , In such an implementation, the images identified in the search results may be used as the image set for the display in the corresponding display zone. A visual indication that the search results are being used as the image data storage for the display zone is possible. An example of such A visual cue can be the overlay of an image on a part of the display area. Another way to provide the search results is a listing. The listing may include sorted or unsorted images that at least partially match the specified search criteria. An image within the collection can be selected and selected via the corresponding display area in the interactive image viewer 102 being represented.

Another exemplary control, in the upper control panel 120a or in the lower panel 120b Being involved is a random control. The random control, when activated, may cause the browsing service to identify a picture randomly or pseudo-randomly for presentation via the corresponding display zone. For example, if the random control in the lower control panel 120b is enabled, the browsing service may randomly or pseudo-randomly select an image from an image data store for the lower display zone 106 choose. The selection may include generating a pseudo-random value and then identifying an image from the image data store using the pseudorandom value.

In some implementations, the selection may also include the random or pseudo-random selection of a data store of images. For example, the browsing service may first determine which source / sources of images to use (e.g., access device image data storage, third-party data storage, and / or catalog system (s)) and then identify an image from the identified source. When randomization is enabled, the corresponding display zone may display an optical indication during the selection process. For example, if the randomization for the upper display zone 104 is activated, the upper display zone 104 show a blurred image sequence to provide feedback about the status of the requested action. Sound or other feedback can be through the user interface 100 or the access device with the user interface 100 being represented.

Another exemplary control, in the upper control panel 120a or in the lower panel 120b can be included is a "find similar" control. If the Find Similar control is enabled, the browsing service may search a catalog system for images related to articles displayed in the portion displayed in the associated display zone. If z. For example, the search function in the upper panel 120a is enabled, the one in the upper display zone 104 shown part of the subject as a search criterion for a catalog search for transmission to a catalog system.

After performing the catalog search, the search results can be accessed through the user interface 100 to be provided. One way to get the results of the catalog search is to use the interactive image viewer 102 , In such an implementation, the images identified in the catalog search results may be used as an image set for display in the corresponding display zone. A visual indication that the results of the catalog search are used as data storage for the display zone images is possible. An example of such a visual cue may be the overlay of an image on a portion of the display zone. Another way to get the results of the catalog search is to list. The listing may contain sorted or unsorted images that at least partially match the specified search criteria. An image within the collection can be selected and selected via the corresponding display area in the interactive image viewer 102 to get presented.

Activation of a controller can interact with a user interface area 100 include. For example, in one implementation of the user interface 100 the browsing controls 110 . 112 . 114 and 116 be omitted as displayed controls. In such implementations, an interaction (e.g., gesture) may occur within the user interface 100 or part of it, such as the interactive image viewer 102 or one of the display zones. The interaction may be associated with a threshold that indicates a degree of interaction that triggers a system response. For example, a finger swipe may be in the upper display zone 104 with low contact pressure and / or a small distance compared to the width of the upper display zone 104 below the threshold. Such wiping may be inadvertent or accidental and may not express a user's image browsing intent. Has the finger wiper a higher contact pressure and / or a greater distance than the width of the upper display zone 104 , the wiping action may indicate a user's intention in the upper display zone 104 change displayed image. In the case of a wiping interaction, wiping may include both a size (eg, pressure or distance) and a direction (eg, from left to right, from right to left, from top to bottom, from bottom to top). The interaction information may be used when the threshold is exceeded to determine how to set the display zone. For example, a swipe from left to right in the upper display zone 104 the user interface 100 change, as in 1B shown. Other examples of interactions may include tapping the access device, shaking the access device or an input coupled thereto, selecting a place of the user interface 100 be the recognition of a spoken command by speech recognition or the like.

The control panel may include a preference control configured to receive preference input information for the image and / or article displayed in the respective display zone. As in 1A As shown, the preference control can be realized with an image such as a star. When preference control is enabled, the browsing service may receive an indication about the image and / or article displayed in the corresponding display zone. This preference can be stored with the image or in a browsing service datastore. The setting can be used to select the in the interactive image viewer 102 to dynamically control images to be displayed. For example, the preference information can be used to organize search results so that images or articles with a specified preference are displayed before images or articles without preference. The preference information may be used to weight the randomization so that images or images with preferred articles are more likely to be displayed than those without preference mapping.

The control panel may include a sharing controller configured to communicate information about the picture and / or item displayed in the respective display zone to a third party. As in 1A shown, the release control via a symbol such. B. an envelope can be realized. When sharing control is enabled, the browsing service may receive an indication about the image and / or article displayed in the corresponding viewing zone. A message may be sent to a third party displaying the image and / or the article in the respective display zone. For example, if a user wants to show his friends a new article through a social media service, enabling the share control may be the user interface 100 to get the information needed to send the image to the social media service. Other sharing options may include emails, text messages, instant messaging, messages to another access device configured to display another instance of the user interface, or the like.

The control panel may include an erase control configured to communicate information about the image and / or article displayed in the respective display zone to the browsing service for deletion. As in 1A shown, the deletion control via a symbol such. As a stylized letter X can be implemented. The deletion may cause the browsing service to delete the image from the image data store. In some implementations, the deletion may not remove the image from the image data store, but may include the identified image in a data set of images to remove the image from further consideration by the browsing service, but the image in the image data store to keep.

In 1A . 1B and 1C becomes the user interface 100 in the context of a web browser with tabs. In some implementations, the user interface may be 100 be presented via a stand-alone client with similar, additional or fewer controls. The number and type of controls may depend on the capabilities of the access device that the user interface 100 represents. Contains the access device z. As a touch screen, can be dispensed button controls in favor of appropriate gesture controls. In one implementation, the user interface may 100 only the interactive image viewer 102 present. Additional controls, as in 1A . 1B or 1C can be shown through an interaction with the user interface 100 to get presented. For example, part of the interactive image viewer 102 be activated (eg, clicked, tapped, etc.) to cause the presentation of a control field.

2 is a block diagram illustrating an illustrative operating environment 200 Fig. 3 shows that an access device providing a browsing service allows the user to access the catalog system via user interfaces such as those described in 1A . 1B and 1C shown to browse. The environment 200 can be a catalog system 210 include. The catalog system 210 can be included to provide a central repository of articles that users can access. The catalog system 210 offers users the opportunity to For example, you may interactively browse, search, review, rate, mark, buy (or otherwise acquire), sell, or obtain referrals for catalog items such as home appliances, electronics, books, clothing, jewelry, and the like. Examples of such systems are described in more detail, for. In U.S. Pat. Nos. 7,685,074; 7,472,077 and 8,122,020, each of which is incorporated herein by reference in its entirety.

The catalog system 210 can be organized so that certain users have entries in the catalog system 210 can add or update. The entries can be in the article data memory 230 be saved. Adding or changing entries influences which entries contain information (eg. Description, color, various images) for searching and presentation by the catalog system 210 are suitable. For example, the catalog system 210 contain a collection of information about articles offered for sale over the Internet. In some implementations, users initiating the transmission of information about an article may download the article information from a remote device for loading into the catalog system 210 to transfer. After inclusion in the catalog system 210 a user can use the catalog system 210 Browse to the item data from the item data store 230 to obtain.

As shown, an access device 300 a catalog search request to a catalog system 210 over a network 208 send. The access device 300 can be an electronic communication device that is configured to send machine-readable messages to the catalog system 210 transmitted. Non-limiting examples of the access device 300 are a personal computing device, laptop computing device, handheld computing device, terminal computing device, mobile device (eg, cell phones or tablet computing devices), network access portable device, and program execution capabilities (eg, "smart eyewear" or "smart Watches "), wireless device, electronic reader, media player, home entertainment system, game console, set-top box, network-access television and program execution capabilities (eg" smart TVs ") or other electronic devices or devices. The messages can be formatted according to a standardized protocol such as TCP / IP, HTTP, FTP or similar. The transmission may be wired, wireless or via hybrid wireless networks.

The catalog search request can input text such as: B. include a search term. In other embodiments, the catalog search may also include audio data representing a user's utterance. In some implementations, the catalog search may be an image search and image data from one or more display zones of the user interface 100 include.

One in the catalog system 210 included search engine 220 can receive the catalog search. The search engine 220 can be configured to look for items in the item data store 230 using the criteria specified in the catalog search. For example, if the catalog search request includes audio data, the search engine may 220 be configured to receive a transcription of the audio signal from an automatic speech recognition system. Using the transcription or if the search term is provided in text form in the catalog search request, the search engine can 220 Article in the article data storage 230 identify. The identification may be a literal identification (eg exact match between item data and the catalog request). The identification may be a partial match (eg words with similar strains or synonyms). In some implementations, the search may be against an index of the article data store 230 be performed.

When identifying articles, the information about the articles may also be taken from the article data store 230 be retrieved. The information about an article may include one or more images for the article, a textual description of the article, user ratings of the article, manufacturer information for the article, a catalog identifier that uniquely identifies the article within the catalog system, and the like. The information about the identified articles can be obtained from the search engine 220 be provided as a search result. The search result may be in some implementations to the access device 300 be transmitted. Accordingly, articles about the catalog system 210 from one in the article data memory 230 filed article catalog can be searched and retrieved.

The access device 300 can be a browsing service 380 include. The browsing service 380 can be configured to use the user interface 100 and receives activation information from controllers on it as related to 1A . 1B and 1C are described. A user interface module 382 can in the browsing service 380 includes his. The user interface module 382 can be configured to be the user interface 100 generates, receives activation information and executes the browsing functions indicated by respective activations. This can be the retrieval of images from one in the access device 300 contained image data memory 330 include. As described above, it may be desirable to ensure the correct alignment of the image portions within and between the display zones. An image segmentation module 386 and an image alignment module 384 can in the browsing service 380 be included to help align the images. The image segmentation module 386 can be configured to segment images into corresponding parts. The segmentation may be based on modeling information stored in a modeling data store 334 are stored. The image orientation module 384 may be configured to vertically and / or horizontally align the image portions identified for display in the respective display zones. The alignment may be based on modeling information stored in the modeling data store 334 are stored. In some Implementations can use the image alignment module 384 be configured to align images through the image alignment module 386 were segmented.

In some implementations, you can access one or more elements of the browsing service 380 over the network 208 instead of the access device 300 be accessed. Likewise, an image data source such as the image data memory 330 and / or the modeling data store 334 via the access device 300 be accessible. For example, the modeling data in the catalog system 210 stored and from the access device 300 over the network 208 be retrieved.

The in the access device 300 Elements contained can be over a bus 390 be coupled. The bus 390 may be a data bus, communication bus, or other bus mechanism, so that the various components of the access device 300 Exchange information.

3 illustrates a general architecture of an exemplary access device 300 which provides a browsing service for the efficient and interactive browsing of articles and / or images managed by the catalog system incorporated in 2 will be shown. The access device 300 can be a processing unit 340 , a browsing service 380 , a network interface 345 , a computer-readable drive 350 , an input / output interface 355 and a memory 370 include. The network interface 345 can connect to one or more networks or computer systems. The processing unit 340 can over the network interface 345 Receive information and instructions from other computing systems or services. The network interface 345 can also store data directly in memory 370 to save. The processing unit 340 can via the input / output device interface 355 with the memory 370 communicate and send information to an optional display 360 output. The input / output device interface 355 can also input from the optional input device 365 such as keyboard, mouse, digital pen, microphone, mass storage device, touch screen, gesture recognition system, speech recognition system, image recognition by an imaging device (which can capture eye, hand, head, body tracking data and / or placement), gamepad, accelerometer, gyroscope, or others known in the art Accept input devices. An example of an input is a swipe received via a touchscreen. Another example of an input is activation by mouse click on one in the user interface 100 included control.

The memory 370 may contain certain computer-executable instructions that the processing unit 340 or perform another computing device in communication with the data store to implement all or part of one or more embodiments. The memory 370 may include RAM, ROM and / or other persistent non-transitory computer-readable media. The memory 370 can be an operating system 374 store the computer program instructions for use by the processing unit 340 or other elements of the access device in the general management and operation of the access device 300 provides. The memory 370 may also include computer program instructions and other information for implementing aspects of the present disclosure.

For example, the memory includes 370 in one embodiment, instructions for the browsing service 380 , The instructions may have specific instructions for the image alignment module 384 , the image segmentation module 386 and the user interface module 382 include. The store can also have a browsing configuration 388 contain. The browsing configuration 388 may include thresholds, image information storage, user information for accessing a catalog system, or other described configuration values. The browsing configuration 388 can store certain values for a specific configuration parameter, such as For example, the interaction threshold for enabling a control. The browsing configuration 388 In some implementations, it may store information to obtain values for a particular configuration item. For example, a control interaction threshold or remote image datastores may be specified as a network location (eg, URL) in conjunction with username and password information to access the network location and obtain the control interaction threshold or the list of remote image datastores. The memory 370 can also have one or more additional data storage such as the image data storage 330 or the modeling data store 334 include or communicate with them.

The in the access device 300 included items can be over the bus 390 be coupled. The bus 390 may be a data bus, communication bus, or other bus mechanism, so that the various components of the access device 300 Exchange information.

In some embodiments, the access device 300 contain additional or fewer components than in 3 shown. For example, an access device 300 more than one processing unit similar to the processing unit 340 and / or more than a computer readable Media drive similar to the computer readable media drive 350 contain. In another example, the access device 300 not with an ad 360 or an input device 365 be coupled. In some embodiments, two or more access devices together may form a computer system for performing features of the present disclosure.

4 Figure 11 is a flowchart illustrating an example method for browsing article images implemented in the catalog system. This in 4 shown method 400 may be wholly or partly by the devices described herein, such as. For example, the user interface module 382 the access device 300 in 2 and 3 to be implemented.

The procedure 400 starts at block 405 in which a display area is provided with a first display zone and a second display zone. A non-limiting example of a display area is the interactive image viewer 102 as he is in 1A . 1B or 1C will be shown. The provision of the display area may include providing a user interface including the first display zone and the second display zone. The user interface can be the one in 1A . 1B or 1C presented user interface 100 be similar to. At block 410 a part of a first image is identified for presentation in the first display zone. The first image can be identified randomly or semi-randomly. The first image may be identified from an image data store included in the device that provides the display area. In some implementations, the first image may be identified from a networked image data store that is accessible from the device that provides the display area over a network connection. As part of the identification of the first image, a part of the first image can also be identified for presentation. The part can be identified by the display area associated with the first display zone. If z. For example, if 30% of the display area is associated with the first display zone, 30% of the image may be identified as a part to be presented. The first part may be identified by segmenting the first image, as described in greater detail below.

At block 415 a part of a second image is identified for presentation in the second display zone. As with the first image, the second image can be identified randomly or semi-randomly. The second image may be identified from an image data store included in the device that provides the display area. In some implementations, the second image may be identified from a networked image data store that is accessible from the device that provides the display area over a network connection. The second image can be identified from a different data store than the first image. As part of the identification of the second image, a part of the second image can also be identified for presentation. The part can be identified on the basis of the display area assigned to the second display zone. If z. For example, if the second display zone is associated with 70% of the display area, 70% of the image may be identified as the portion for presentation. The second part may be identified by segmentation of the second image, as described in greater detail below.

At block 420 the first part of the first image and the second part of the second image are displayed in their respective display zones. In some implementations, block 420 include causing display of the first part of the first image and the second part of the second image in their respective display zones. The display can be triggered by one or more messages, the z. B. between the access device 300 and the catalog system 210 be transmitted. Displaying the parts may include rendering the part of the images on a display device. Displaying the parts may also involve aligning the parts to obtain a continuous view of the subject. The alignment features are explained in more detail below.

At block 430 it is determined whether an interaction has been detected within the first display zone. The determination may include monitoring the first display zone for an input that exceeds an interaction threshold. The determination may also include detecting the activation of a controller associated with the first display zone. If the determination at block 430 is negative, the process returns 400 to block 420 back to present the first part and the second part further. Is the determination at block 430 positive, the procedure goes 400 to block 435 above.

At block 435 the image data presented via the first display zone are set. The setting may depend on the type of interaction detected. For example, if the interaction wipes across the in 1B shown upper display zone 104 from right to left of the upper display zone 104 was, the setting may include removing the first part from the first display zone from right to left, leaving the first part 140 no longer the only part of the upper display zone 104 shown subject is. The adjustment may also include replacing the first part with a replacement part of a third image. As in 1B shown, the third part occurs 142 in the upper display zone 104 one. The spare part may be random or pseudo-random from one Image memory to be selected. The spare part can also be played from right to left when the first part is removed from the first display zone.

If the nature of the interaction was an image adjustment, the first part within the first display zone may be shifted proportionally to the extent of the interaction. For example, the user may be the first part 140 manually with the second part 144 in 1A Align or move one or both parts for a more aesthetically accurate view of the entire subject. The interaction may be dragging within the first display zone (eg, the upper display zone 104 ), which indicates the direction and amount of movement on the first part (eg the first part 140 ) should be applied. The procedure 400 may end with the adjustment of the display zone in response to the detected interaction. All or part of the procedure 400 can be repeated with the replacement part and the second part to allow further browsing and interacting via the user interface.

Segmentation can be used to identify the part of an image for presentation via a display zone. In the exemplary garment implementation, an image of a person may show the person wearing various articles. Therefore, it may be desirable to segment images to identify each category of subjects in an image. One way to segment an image is to use a structural model.

5A Figure 11 is a pictorial diagram of an illustrative structural model for a subject appearing in an image. The picture in 5A also includes fourteen structural reference points labeled M through Z. For example, the structural reference is 530R the structural reference point R, located approximately at the left shoulder of the subject 120 located. Each of the in 5A The structure references shown also contain at least one path to another structure reference. For example, the structure reference has 503R a path 545a to the structure reference 530s and another path 546b to the structure reference 530q , Each path is assigned a distance indicating the distance between the nodes associated with the path (e.g., structural references). The collection of structure references and paths forms a structural graphic for the subject. If the subject is a human, the structural diagram can be called a skeletal model.

5B is a pictorial diagram of the picture in which the subject appears, which corresponds to the structural model of 5A is mapped. The mapping can be done by taking the structural diagram for the subject, e.g. From the modeling data store 334 , be performed. Using data in the image of the subject, the nodes of the structural model can be mapped to positions in the image. The positions can be identified by comparing depth information for the pixels contained in the image with the node values for the structural model. In some implementations, feature recognition may be used to identify positions for the placement of the nodes of the structural model. For example, face recognition can be used to identify the subject's face as shown in the picture. Once identified, the node M can be placed at the identified location.

Once the structural diagram is mapped to the image, collections of nodes may be associated with different segments of the represented subject. For example, the nodes X, W, U, V, Y, and Z are mapped to a part of the image showing the legs of the subject. The collections of nodes and links to segments can be stored in a data store to which the image segmentation engine is attached 386 In some implementations, the node collections can be stored in conjunction with the structure diagram.

The image can be divided into parts based on a desired segment via the interactive image viewer 102 should be presented. For example, if the picture is to be taken in the upper display zone 104 is selected, a portion of the image showing the top half (eg, torso and head) of the subject may be needed.

5C shows a part of the image that is in 5B segmented to show the part of the image that corresponds to the subject's torso and head. Similarly, if the picture is in the lower display zone 106 is to be shown, a portion of the image showing the lower half (eg, legs) of the subject is needed.

5D shows a part of the image that is in 5B is shown segmented to show the part of the image corresponding to the legs of the subject. Further details on structural models and image segmentation are presented in the June 3, 2015 U.S. Patent Application No. 14/729894 which is jointly owned and incorporated by reference.

Another way to segment images is a relationship model. A relationship model typically defines areas within an image in which expected parts (eg body parts) of a subject. The ranges can be specified as bounding boxes. In some implementations, the ratio model may be expressed as a percentage such that the 1/5 of the image generally shows the head of the subject, the next 2/5 of the image the torso and the remaining 2/5 the legs.

6A illustrates an illustrative ratio model for segmentation. The illustrated ratio model comprises the three segments 602 . 604 and 606 , The height of the ratio model is shown as x. Each part can be defined as a proportion of the total size of the display area (eg height x). The size of the parts can be determined by machine learning. For example, a set of manually segmented images may be provided to train a segmentation model to determine ideal sizes for the segmentation of images that have not yet been processed by the system. The training may also include the consideration of image data such as the gender of a subject shown, the race of the subject shown, the body type of the subject shown, or the location where the image was taken.

The sizes of the parts can be determined using image recognition techniques whereby the person calibrates the ratio model by standing in a predetermined pose and analyzing the position of certain image features (eg, neck, face, hands, hips, feet, etc.). The size of the parts can be through the user interface 100 be determined. For example, the user can access a configuration interface that allows the segmentation of the images to be adapted to the respective body type. The configuration interface may include adjustable segmentation lines, typically the partition boundaries in the interactive image viewer 102 can correspond.

6B provides an image input for segmentation using the ratio model of 6A as in 6B shown, is the input image 610 not as high as the relationship model. To apply the ratio model, the input image is therefore first normalized to the same level as in the ratio model. Normalization may include receiving image data, including in some implementations of depth information, and adjusting the received image to provide a normalized image.

6C represents a normalized image consistent with the relationship model of 6A was generated. The normalized input image 620 has the same height as the relationship model. Therefore, the height information for each part of the input image can be used to split the normalized input image. Parts contained in the relationship model may be associated with a particular feature of the subject 6C shown, the relationship model includes the segment 602 with the head, the segment 604 with the hull and the segment 606 with the legs.

One or more of the segments identified via the relationship model may be via the interactive image viewer 102 be provided for display. For example, if three display zones are used, the display zone for the fuselage can be the one in 6D use shown portion of the normalized input image. 6D shows a portion of the segmented image to show the portion of the image that corresponds to the subject's torso.

A relationship model and a structural model are two examples of model-driven image segmentation. Other image segmentation models can be used to create image segments. For example, computer vision models can be used to process images to identify features (e.g., garments, body parts) shown therein. An example of a computer vision model is a neural network model. The neural network model can be trained on annotated image data, the annotations indicating features of interest. The neural network model can take into account each pixel in the image and assign the pixel to a feature. Since the annotated images are processed by the neural network model to produce predicted features, the predictions are compared with the annotated features. The parameters of the model can be set so that the predictions better match the commented features. Once the neural network model is trained, unknown images can be processed to identify segments for the image. Other computer vision techniques that can be used for segmentation are subject location, semantic segmentation, edge detection, and the like.

7 Figure 5 is a flowchart illustrating an example method implemented in the browsing service. This in 7 shown method 700 may be wholly or partly due to the devices described here, such as the image alignment module 384 and / or the image segmentation module 386 of in 2 and 3 shown access device 300 be implemented. Once segments have been identified for presentation, it is possible that the individual segments are no longer aligned to provide a complete view of the subject. For example, if the subject is shown off-center in a first part, the view may of the presented subject, when the first and segments are combined, provide a discontinuous view that does not provide a realistic representation of the subject. Accordingly, the segments may be further processed to align the identified segments.

At block 705 a first image part is generated from a first image. The first image portion may be generated by segmenting an image from an image data memory as described herein. At block 710 a second image part is generated from a second image. As with the first image part, the second image part can be generated by segmenting a second image from an image data memory as described herein.

At block 715 the first image part and the second image part are presented via a display. The presentation may be displaying the parts in an interactive image viewer such as the one in 1A shown interactive image viewer 102 include. At block 720 It is determined whether the first and second image parts include centerlines. A centerline is a logical line that indicates the center of the subject shown in the image, from the horizontal top of the image portion to the horizontal bottom of the image portion. Some segmentation techniques, such as Skeleton modeling, may provide centerline information. If the parts contain centerlines, at block 725 the center line of the first image part and the center line of the second image part aligned to a continuous line.

After aligning the centerlines, if any, or if midlines are not present, the procedure may be 700 at block 730 an additional orientation of the image parts based on color. At block 730 For example, a pixel color value for one pixel from the first image part may be compared with a pixel color value for another pixel from the second image part. In some implementations, the pixel may be from the first image portion adjacent to the pixel from the second image portion. In some implementations, the pixel of the first image portion may be within a threshold distance to the pixel of the second image portion. If the comparison of the color values indicates that the pixels are similar, the images may be considered aligned. So z. Skin color values may be used to identify skin constituents of a human subject in an image. Typically, the color values for representing a person's skin tone are relatively the same across all images. The equality can be improved by normalizing the color values for the pixels contained in the images and / or image parts. An example of such normalization is adjusting the brightness of the pixels. The comparison may include comparing the actual color values of the pixels to a threshold and / or the difference between the color values and a threshold.

At block 735 It is determined whether the pixel color values correspond to an alignment threshold. If, for example, the color value of the first image part lies in the area of the skin tone and the color value of the second image part lies above the skin tone area, the determination can be negative. In such cases, the procedure can 700 with block 740 continue, wherein at least one of the first image part or the second image part is set. The setting may include a horizontal or vertical change in the position of a picture detail. By moving the image part, the image parts can be aligned so that the skin tone areas are substantially aligned so that a realistic image of the subject arises. The setting can be made according to a preset adjustment factor. In some implementations, the extent of adjustment of the image portions may be determined dynamically due to the discrepancy between the pixel color values of the image portions and / or the difference between the adjustment threshold and one or more of the pixel color values.

8A to 8D show the segmentation of two images and the alignment of the segments from the two images according to the in 7 shown method. 8A shows a first input image 802 and a second input image 804 , The first input image 802 and the second input image 804 can to display via the user interface 100 from 1A have been identified. In 8B the subject's poses are identified in each input image. The poses can be identified by image analysis of the images. The image analysis may include determining the pose based on the depth and / or color information contained therein. In some implementations, the pose may be modeled using a structural model such as 5A be identified.

As in 8B , the first input image 802 , shown, the subject's shoulders are identified as points A and B. The shoulders in the second input image 804 are identified as points C and D. The points A and B in the first input image 802 are offset by 20 degrees. This indicates that the subject is depicted in an asymmetrical pose. Accordingly, the first input image 802 be adjusted by 20 degrees to provide a symmetrical view of the subject. In contrast, the shoulders of the subject are as in the second input image 804 shown parallel to the ground, indicating a symmetrical pose.

wobei d_min ein Mindestabstand zwischen Referenzpunkten und d_max ein Maximalabstand zwischen Referenzpunkten ist.In 8C is a shot first picture 806 represented with a center line. The center line for the rotated first image 806 can in terms of the previously Identified structural reference can be identified. In the in 8C The center line halves the distance between the points A and B such that there is an equal distance (x) between the center line and the point A as between the center line and the point B. A similar centerline will be for the second input image 804 identified and in 8C shown. In 8C There is a second equal distance (z) between the center line of the second input image 804 and point D as between the centerline and point D. In some implementations, the distance (z) may be equal to the distance (x). In other implementations, the distance (z) and the distance (x) may be different. In such cases, it may be desirable to have one or both of the rotated first images 806 and the second input image 804 to set the subject in visually consistent proportions when displaying the images. The adjustment may include zooming, scaling, and / or translating image data (eg, pixel information). The adjustment may include taking into account the depth information associated with the image data. In some implementations, the setting may be dynamically limited. For example, the known texture points (eg, point A, B, C, or D) can be used to generate scaling boundaries that indicate the maximum and minimum scaling that can be applied to an image with the texture points. For example, with the second input image 804 out 8C the distance between the shoulder points C and D are expressed as (2 * z). It may be desirable not to scale the image such that the scaled image shows those points at not less than a minimum distance and not more than a maximum distance. One way to express the scaling limits is shown in Equation 1 below. $$\left(Maßsta{b}_{min}.Maßsta{b}_{max}\right)=\left(\frac{d_{min}}{2z}.\frac{d_{max}}{2z}\right)$$

where d _{min is} a minimum distance between reference points and d _{max is} a maximum distance between reference points.

wobei g ein Wert ist, der das Geschlecht eines im zu zoomenden Bild gezeigten Subjekts angibt; a ist ein Geschlechtgewichtungsfaktor für den horizontalen (x) Zoom; und zoom_{x min} .ein Wert, der den minimalen horizontalen (x) Zoomfaktor angibt.In some implementations, the adjustment factor may be further determined based on information about the subject shown in the picture. For example, it may be desirable to determine the gender of the subject. Depending on gender, specific attitudes can be made more aggressively than others. For example, to avoid enlarging an image to give a visual impression of a large waist for men, the adjustment factor can be weighted to allow more aggressive vertical scaling than horizontal scaling. Equation 2 below is an expression of dynamic adjustment factor determination to identify a minimum horizontal zoom factor based on information about a subject shown in the image. Specifically, Equation 2 provides an example expression for determining a minimum horizontal zoom factor for a subject of identified gender (zoom _{x min} (G)). $$ZOO{m}_{x_{min}}\left(G\right)=\alpha \left(G\right)ZOO{m}_{x_{min}}$$

where g is a value indicating the gender of a subject shown in the image to be zoomed; a is a gender weighting factor for the horizontal (x) zoom; and zoom _{x min} .a value indicating the minimum horizontal (x) zoom factor.

8D shows the segmented image parts 808 and 810 that align with the centerlines of each image. The segmentation can be carried out according to the segmentation method described above, for. With respect to 5A . 5B . 5C . 6A . 6B . 6C or 6D , In some implementations, the segmented images may be further processed to improve the final formatted view. So z. On the left and right sides of the part 810 still visible parts of the fingers of the subject. These "floating" elements may be blurred or removed from the segment to enhance the visual quality of the final presentation. The floating elements can be identified by color evaluation, edge detection or other image processing techniques. In some implementations, pixels may be along the adjacent edges of the parts 808 and 810 be set to smooth the transition from one part to the other. The smoothing may include blurring pixels, adjusting the transparency of the pixels, blending pixel values, performing a repair, dodging and re-exposing, or other functions on the pixels or other image / pixel manipulations.

In some implementations, the partition information can be used to identify a location where the smoothing should be performed. The smoothing may take into account pixels along adjacent edges or within a tolerance of the edge (eg, a neighborhood of 3, 7, 10, or more pixels). The tolerance can be specified and stored as a configuration value. In some implementations, the tolerance may be dynamically generated based on factors such as partition information, image data, image source, information about elements or subjects shown in a part, and the like. Depth information can be used to mask areas for smoothing. For example, a first smoothing process may be performed using a background of a first part and a background of a second part. A second smoothing operation can then be applied to the foreground of the first part and the foreground of the second part. In some implementations, a third smoothing process may be provided for processing areas in which the foreground of the first part meets the background of the second part. Likewise, another smoothing process may include areas where the background of the first part meets the foreground of the second part.

The system can store a pose definition to identify a pose. The pose definition may include information that identifies, for a subject positioned in the pose, a centerline for the pose and a position of two or more points relative to each other on the subject. For example, the two points may be a first shoulder and a second shoulder of the subject. For a particular image, the dots may be based on the data contained in the image or related to the image, e.g. B. depth information can be identified. By correlating the position of the points shown in the picture with the points identified in the pose definition, the pose associated with the pose definition can be determined. The system can provide the centerline from the pose definition as the centerline for the image.

Depending on the embodiment, certain acts, events, or functions of any of the processes or algorithms described herein may be executed, added, merged, or omitted in a different order (eg, not all described acts or events are necessary for the practice of the algorithm). Additionally, in certain embodiments, processes or events may be performed simultaneously rather than sequentially, e.g. By multi-threaded processing, interrupt processing or multiple processors or cores, or other parallel architectures.

The various illustrative logical blocks, modules, routines, and algorithm steps described in connection with the embodiments presented herein may be implemented as electronic hardware or as a combination of electronic hardware and executable software. To illustrate this interchangeability, various illustrative components, blocks, modules and steps have been generally described in terms of their functionality. Whether this functionality is implemented as hardware or software running on hardware depends on the particular application and design conditions of the overall system. The described functionality may be implemented differently for each individual application, but such implementation decisions should not be interpreted as a departure from the scope of the disclosure.

Moreover, the various illustrative logic blocks and modules described in connection with the embodiments illustrated herein may be implemented or executed by a machine, such as a computer. An image browsing device, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination that was developed to perform the functions described here. An image browsing device may be or may include a microprocessor, but alternatively, the image browsing device may be or include a controller, a microcontroller, or a state machine, combinations thereof, or the like, that are configured to receive image data and display. An image viewer may include an electrical circuit configured to process computer-executable instructions. Although described above all with respect to digital technology, a picture search device may also include primarily analog components. For example, some or all of the browsing service algorithms described herein may be implemented in analog circuits or mixed analog and digital circuits. A computing environment may include any type of computer system, including, but not limited to, a computer system based on a microprocessor, a mainframe, a digital signal processor, a portable computing device, a device controller, or a computing machine in a device, to name but a few ,

The elements of a method, process, routine or algorithm described in connection with the embodiments presented herein may be implemented directly in hardware, in a software module executed by a composite image processing device, or in a combination of both , A software module may be in random access memory (RAM), flash memory, read only memory (ROM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), registers, hard disk, a removable disk, a read-only memory (CD-ROM), or any other form of non-transitory computer-readable storage medium. An exemplary Storage medium may be coupled to the image browsing device so that the image browsing device can read and write information from the storage medium. Alternatively, the storage medium may be integrated with the image browsing device. The image browsing device and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in an access device or other image processing device. Alternatively, the image searcher vice and the storage medium may be located as discrete components in an access device or other image processing device. Some implementations may be a computer-implemented method that may be executed under the control of a computing device, such as a computer. An access device or other image processing device, executes and executes certain computer-executable instructions.

The embodiments disclosed herein may include a computer-implemented method under control of a computing device that executes certain computer-executable instructions, including one or more of the following: receiving horizontal partition information for an interactive display area, wherein the horizontal partition information is a first display zone that is over a horizontal partition , and identifying a second display zone located below the horizontal partition, identifying a portion of a first image of a subject for presentation in the first display zone, wherein the portion of the first image identifies using a size of the interactive display area and the horizontal partition information where the portion of the first image may correlate to a first area of the interactive display area covered by the first display zone part of a second image of the subject to be presented in the second display zone, wherein the portion of the second image may be identified using the size of the interactive display area and the horizontal partition information, the portion of the second image correlating to a second amount of the interactive display area For example, when the portion of the first image in the first display zone and the portion of the second image in the second display zone are presented, detecting an interaction with the first display zone in a first direction relative to the horizontal Partition, determining that the interaction meets a threshold, selecting a third image from an image data source, identifying a portion of the third image to be presented in the first display zone, the portion of the third image using the size of the interactive display and the horizontal partition information can be identified, wherein the portion of the third image correlates with the first amount of the interactive display area covered by the first display area, causing the portion of the first image from the first display area to travel along the first direction interactive display area is moved and / or cause the part of the third image in the first display area along the first direction is moved into the interactive display area to replace the part of the first image.

Optionally, the selection of the third image may include one or more of: identifying a category for an article shown in the portion of the first image, browsing an image data store using the category, and / or receiving the third image in response to the search , where the third picture shows another article from the category. Optionally, the computer-implemented method may also include one or more of the following: detecting a second interaction with the first display zone in the first direction relative to the horizontal partition; Determining that the second interaction does not satisfy the threshold and / or adjusting the portion of the first image of the subject presented in the first display zone based on an amount of interaction and the first direction. Optionally, the computer-implemented method may also include one or more of: storing the horizontal partition information, information identifying the part of the second image presented in the second display zone, and information representing the part of the first image presented in the first display zone in a session record identifying, generating a record identifier for the session record, receiving the record identifier, retrieving the session record using the record identifier, and / or making a setting on at least one of the horizontal partitions, the first display zone, and the second display zone of the interactive display area to access the interactive display area To show part of the first image within the first display zone and the part of the second image within the second display zone.

The embodiments disclosed herein may include a computer-implemented method under the control of a computing device that executes certain computer-executable instructions that include one or more of the following: identifying a portion of a first image of a first article for presentation in a first display zone of a display region; of the first image may correlate to a first area of the display area detected by the first display area, identifying a part of a second image of a second article to Presenting in a second display zone of the display area, wherein the portion of the second image may correlate to a second area of the display area covered by the second display zone, causing the presentation of the portion of the first image in the first display zone and the presentation of the portion of the second image in the display area second display zone, detecting an interaction with the first display zone and / or adjusting image data presented via the first display zone based on the interaction.

Optionally, the interaction may include an amount of interaction and an interaction direction, wherein adjusting the image data presented via the first display zone may include adjusting the portion of the first image of the subject presented in the first display zone based on the amount of interaction and the direction of interaction. Optionally, the interaction may include an extent of interaction and an interaction direction, wherein adjusting the image data presented via the first display zone may include one or more of: determining that the extent of interaction exceeds an interaction threshold; Selecting a third image; Identifying a portion to be presented in the first display zone, wherein the portion of the third image may correlate to a first area of the display area covered by the first display zone, and / or causing the portion of the first image in the first display zone to be presented by presenting the part of the third image is replaced.

Optionally, causing the presentation of the portion of the first image from the first display zone to be replaced may include causing the portion of the first image from the first display zone to appear as leaving the display area along the direction of interaction, and causing the presentation of the part of the third image as a shift into the display area along the direction of interaction takes place. Optionally, the selection of the third image may include one or more of the following: identifying a category for the first article shown in the portion of the first image, browsing an image data store using the category and / or receiving the third image in response to the image Browsing the image data store, where the third image can show another article from the category.

Optionally, the computer-implemented method may further include one of the following: generating a pseudorandom value and / or selecting the third image from a set of images received in response to the search in the image data store using the pseudorandom value. Optionally, browsing the image data storage may include communicating a search query over a network to the image data store, and causing the presentation of the third image may include causing the presentation of a visible artifact for a portion of the article as shown in the portion of the third image; wherein the visible artifact indicates that the third image was received from the image data store.

Optionally, the computer-implemented method may also include one or more of the following: storing information identifying the portion of the second image presented in the second display zone and information identifying the portion of the first image presented in the first display zone in a session record; Create record identifiers for the session record, receiving the record identifier, retrieving the session record using the record identifier, and / or causing a setting on at least one of the first display zone and the second display zone to display, via the display area, the portion of the first image within the first display zone and the portion of the second image within the second display zone. Optionally, the computer-implemented method may further include one or more of: receiving horizontal partition information about the display area, the horizontal partition information identifying the first display zone above a horizontal partition and the second display zone below the horizontal partition, the portion of the first image and the part of the second image can be identified using a size of the display area and the horizontal partition information.

The embodiments disclosed herein may include a system having one or more of a data store storing particular computer-executable instructions and a computing device in communication with the data store, the computing device including a processor that executes certain computer-executable instructions that the system allocates one or more of the following: identifying a portion of a first image of a first article for presentation in the first zone of a display area, wherein the portion of the first image may correlate to a first area of the display area detected by the first zone, identifying a portion of a second one An image of a second article for presenting in a second zone of the display area, wherein the portion of the second image may correlate to a second area of the display area covered by the second zone, causing the presentation of the portion of the first Picture in the first zone and the presentation of the part of the second image in the second zone, detecting an interaction with the first zone and / or adjusting image data presented over the first zone based on the interaction.

Optionally, the interaction may include an extent of interaction and an interaction direction, wherein the processor may execute the particular computer-executable instructions to adjust the image data presented over the first display zone by causing the system to include at least the portion of the first image of the subject presented in the first zone based on the extent of interaction and the direction of interaction. Optionally, the interaction may include an interaction extent and direction of interaction, wherein the processor may execute the particular computer-executable instructions to adjust the image data presented over the first display zone by causing the system to: determine that the interaction extent is an interaction threshold exceeding, selecting a third image, identifying a portion to be displayed in the first zone, wherein the portion of the third image may correlate to a first area of the display area covered by the first display zone, and / or causing the portion of the first image to be presented in the first zone is replaced by presenting the part of the third image.

Optionally, the processor may execute the particular computer-executable instructions to cause the presentation of the portion of the first image to be replaced by the first zone by at least causing the system to present the portion of the first image from the first zone as Leaving the display area along the direction of interaction occurs, and / or possibly causing the presentation of the portion of the third image in the first zone as a shift into the display area along the direction of interaction. Optionally, the processor may execute the particular computer-executable instructions to select the third image by causing the system to do one or more of the following: identifying a category for the first article shown in the portion of the first image, browsing an image data store at Using the category and / or receiving the third image in response to browsing the image data store, wherein the third image may show another article from the category.

Optionally, the processor may execute the particular computer-executable instructions to further cause the system to generate one or more of the following: generating a pseudo-random value and / or selecting the third image from a set of images in response to the search in the image data store using the Pseudo-random value were received.

Optionally, the processor may execute the particular computer-executable instructions to search the image data store by causing the system, at a minimum, to transmit a query to the image data store over a network, and wherein the processor may execute the particular computer-executable instructions to present the third image by causing the system to at least display a visual artifact for a portion of the article, as shown in the portion of the third image, the visible artifact indicating that the third image was received from the image data store.

Optionally, the processor may execute the particular computer-executable instructions to further cause the system to do one or more of: storing information identifying the part of the second image presented in the second zone and information presenting the one presented in the first zone Identify part of an image in a session record, generate a record identifier for the session record, receive the record identifier, retrieve the session record using the record identifier, and / or make a setting on at least one of the first display zone and the second display zone to display the part of the display area first image within the first display zone and the portion of the second image within the second display zone. Optionally, the processor may execute the particular computer-executable instructions to further cause the system to receive one or more of: receiving horizontal partition information about the display area, wherein the horizontal partition information is the first zone above a horizontal partition and the second zone below the horizontal partition wherein the portion of the first image and the portion of the second image may be identified using a size of the display area and the horizontal partition information.

The embodiments disclosed herein may include a computer-implemented method under the control of a computing device executing particular computer-executable instructions, including one or more of the following: receiving a first image of a human subject and a second image of the human subject a fuselage and legs, generating a normalized first image from the first image and a normalized second image from the second image, wherein the normalized first image and the normalized second image show the human subject on a common scale, receiving an image segmentation model for segmenting the normalized first image and the normalized second image, generating a first image part using the image segmentation model and the normalized first image, wherein the first image part showing the body of the human subject, generating a second image portion using the image segmentation model and the normalized second image, the second image portion showing the legs of the human subject, causing the presentation of the first image portion and the second image portion via display, and / or causing presenting the first image part via the display in vertical alignment with the second image part, wherein causing the first image part to be presented via the display in vertical alignment with the second image part, one or me More particularly, detecting the first pose of the human subject shown in the first image, detecting a second pose of the human subject shown in the second image, identifying a first centerline for the first pose, identifying a second centerline for the second pose Pose, and / or causing the first image portion and the second image portion to be presented over the display, wherein the first centerline and the second centerline are aligned.

Optionally, the computer-implemented method may further comprise one or more of: receiving first depth information for the first image and second depth information for the second image, wherein the first depth information and the second depth information may each indicate a distance of the subject from one or more sensors used to capture the first image and the second image, wherein generating a normalized first image and a normalized second image may include scaling at least one of the first image and the second image such that the distance from the one or more Sensors of the subject, as shown in the normalized first image, equal to the distance from the one or more sensors of the subject, as shown in the normalized second image. Optionally, the image segmentation model may include one or more skeletal models for the human subject, wherein the skeletal model identifies a position for the torso and legs of the subject, wherein generating the first image portion of the normalized first image may include mapping the skeletal model to the normalized first image to identify a position of the trunk, and wherein generating the second image portion of the normalized second image may include mapping the skeletal model to the normalized second image to identify a position of the legs, a computer vision model, wherein the computer Vision model for a given image identifies the stem and legs of the subject, wherein generating the first image portion of the normalized first image may include processing the normalized first image using the computer vision model to approximate a position of the stem identify, and where the Generating the second image portion of the normalized second image processing the normalized second image using the computer vision model to identify a position of the legs and / or a ratio model comprising a first portion of an image as a body region and a second portion of the image indicates a leg region, wherein generating the first image part of the normalized first image may include one or more identification pixels from the first image included in the body region indicated by the ratio model; generating the first image part using the pixels from the first image part the first image contained in the stem region, and / or wherein generating the second image part of the normalized second image identifies pixels from the second image contained in the leg region indicated by the ratio model and / or generating the second image part using d it may include pixels from the second image contained in the leg region.

Optionally, detecting a pose of the human subject shown in an image may include one or more of the following: receiving a pose definition identifying the pose, the pose definition including information including a first shoulder position relative to a second shoulder position for a pose positioned in the pose Identify a subject and a pose centerline, identify a first position within the image that shows a first shoulder of the human subject, identify a second position within the image that shows a second shoulder of the human subject, and / or identify the pose definition Comparing the first position and the second position with the information identifying the first shoulder position relative to the second shoulder position. Optionally, the computer-implemented method may also include one or more of the following: identifying a first pixel in the first image part that is within a threshold distance of a second pixel in the second image part, mixing a color value of the first pixel with a color value of the second pixel, to generate a mixed color value, and / or assign the mixed color value to the first pixel.

The embodiments disclosed herein may be a computer-implemented method which is under the control of a computing device that executes certain computer-executable instructions, including one or more of the following: generating a first image portion from a first image, the first image portion showing a first portion of a subject, generating a second image portion from a second image portion Image, the second image portion showing a second portion of the subject, causing the presentation of the first image portion and the second image portion via a display and / or the orientation of the first image portion and the second image portion as presented via the display to be a single view of the image To provide subject including the first part of the subject and the second part of the subject.

Optionally, the computer-implemented method may include one or more of: receiving a skeletal model for the subject, wherein the skeletal model identifies a position for a portion of the subject, wherein generating the first image portion includes mapping the skeletal model to the first image by one position of the first part of the subject shown in the first image, and / or wherein generating the second image part includes mapping the skeletal model to the second image to identify a position of the second part of the subject that is in the second Picture is shown. Optionally, aligning the first image part and the second image part may include one or more of the following: mapping the skeleton model to the second image to identify a position of the first part of the subject shown in the second image, determining a setting factor that sets a position on the second image indicating a second image to align the position of the first part of the subject shown in the second image and the first part of the subject shown in the first image, and / or causing adjustment of the second image part as presented via the display using the adjustment factor.

Optionally, the computer-implemented method may include one or more of the following: receiving a ratio model indicating a first region of an image including the first part of the subject and a second region of the image including the second part of the subject, wherein generating the first image part is on or may include a plurality of identifying pixels from the first image included in the first region indicated by the ratio model, and / or identifying the first image part using the pixels from the first image included in the first region; Generating the second image part may include one or more of the identifying pixels from the second image contained in the second region indicated by the ratio model, and / or generating the second image part using the pixels from the second image contained in the second area.

Optionally, aligning the first image portion and the second image portion may include one or more of: identifying a first centerline for the first image portion, identifying a second centerline for the second image portion, and / or causing a horizontal adjustment to at least one of the first image portions and second image part, as presented over the display, to align the first centerline and the second centerline. Optionally, identifying a centerline for an image may include one or more pose definitions that identify a pose, wherein the pose definition includes information that, for a pose positioned subject, is a pose centerline and a first position of the subject on the subject identifying the second point on the subject, identifying the first point and the second point on the subject shown in the picture, detecting the pose of the subject shown in the picture by correlating the first point on the subject and the second point on the subject Image subject with the first position relative to the second position identified by the pose definition and / or providing the centerline contained in the pose definition as the centerline for the image.

Optionally, the computer-implemented method may further include one or more of: identifying a first pixel in the first image portion that is within a threshold distance of a second pixel in the second image portion; determining that a color value of the first pixel correlates to a subject sound threshold; and / or determining that a difference between the color value of the first pixel and a color value of the second pixel does not correspond to an alignment threshold, wherein causing alignment of the first image part and the second image part causes a horizontal adjustment to be made on at least one of the first image part and the second image part second image portion as presented via the display includes, until the first pixel in the first image portion is within the threshold distance to a third pixel in the second image portion, wherein a difference between a color value of the third pixel and the color value of the first pixel may correspond to the alignment threshold. Optionally, the computer-implemented method may include one or more of the following: identifying a first pixel in the first image part that is within a threshold distance of a second pixel in the second image part, generating a mixed color value using a color value of the first pixel and a color value of the first pixel second pixel and / or assigning the mixed color value to the first pixel.

The embodiments disclosed herein may include a system including at least one of a data store executing particular computer-executable instructions and / or a computing device in communication with the data store, wherein the computing device includes a processor that executes the particular computer-executable instructions to perform the A system for at least one of the following: generating a first image part from a first image, the first image part showing a first part of a subject, generating a second image part from a second image, the second image part showing a second part of the subject, causing the Presenting the first image portion and the second image portion via an indication and / or causing the orientation of the first image portion and the second image portion as presented via the display to be a single view of the subject including the first portion of the subject and the second portion of the sub to provide it.

Optionally, the processor may execute the particular computer-executable instructions to further cause the system to receive one or more of the following: receiving a skeleton model for the subject, the skeleton model identifying a location for a portion of the subject, the instructions provided by the system thereto causing the first part of the image to generate instructions to cause the system to map the skeleton model to at least the first image to identify a position of the first part of the subject shown in the first image, and The instructions causing the system to generate the second part of the image may include instructions to cause the system to map the skeleton model to at least the second image to identify a position of the second part of the subject shown in the second picture. Optionally, the processor may execute the particular computer-executable instructions to cause alignment of the first image portion and the second image portion by causing the system to perform at least one of: mapping the skeleton model to the second image to obtain a position of the first portion of the image identifying a subject, indicating a positional adjustment to the second image to align the position of the first part of the subject shown in the second image and the first part of the subject shown in the first image, and / or causing a subject Adjusting the second image portion as presented via the display using the adjustment factor.

Optionally, the processor may execute the particular computer-executable instructions to further cause the system to do at least one of: receiving a ratio model including a first portion of an image including the first portion of the subject and a second portion of the image including the second portion of the subject wherein the instructions that cause the system to generate the first image portion may include instructions that cause the system to do one of the following: identify pixels from the first image contained in the first region indicated by the ratio model and / or generating the first image portion using the pixels from the first image contained in the first area, and / or wherein the instructions to cause the system to generate the second image portion may include instructions that include Initiate at least one of the following: Identify n of pixels from the second image contained in the second region indicated by the ratio model and / or generating the second image part using the pixels from the second image included in the second region.

Optionally, the processor may execute the particular computer-executable instructions to cause the alignment of the first image portion and the second image portion by causing the system to at least one of: identifying a first centerline for the first image portion, identifying a second centerline for the second image portion Image portion and / or causing a horizontal adjustment to at least one of the first image portion and the second image portion as presented over the display to align the first centerline and the second centerline. Optionally, the processor may execute the particular computer-executable instructions to identify a centerline for an image by causing the system to do at least one of: receiving a pose definition that identifies a pose, the pose definition including information appropriate for one in the image Pose positioned subject and a centerline for the pose and identify a first position of a first point on the subject relative to a second position of a second point on the subject, identifying the first point and the second point on the subject shown in the image, detecting the pose of the subject shown in the picture by correlating the first point on the subject and the second point on the subject shown in the picture with the first position relative to the second position identified by the pose definition and / or providing the centerline contained in the pose definition as the centerline for the subject Image.

Optionally, the processor may execute the particular computer-executable instructions to further cause the system to do one of the following: identifying a first pixel in the first image portion that is within a threshold distance of a second pixel in the second image portion Color value of the first pixel correlates with a subject tone threshold, and / or determining that a difference between the color value of the first pixel and a color value of the second pixel does not correspond to an alignment threshold, wherein the instructions, the system, align the first image portion and the second image portion to cause instructions to cause the system to cause a horizontal adjustment on at least one of the first image portion and the second image portion as presented via the display until the first pixel in the first image portion is within the threshold distance to a third pixel in the second image part, wherein a difference between a color value of the third pixel and the color value of the first pixel correspond to the alignment threshold.

The conditional formulations used here, such as. "May," "may," "may," "may," and so on, unless expressly stated otherwise or otherwise understood within the context in which it is used, are intended to convey, in general, that certain embodiments Elements and / or steps include, while other embodiments do not include these. Thus, such formulations should not generally imply that features, elements, and / or steps are in any way required for one or more embodiments, or that one or more embodiments necessarily include logic to decide whether those features, elements, and / or steps are included or intended to be embodied in a particular embodiment, with or without other input or solicitation. The terms "comprising," "including," "having," and the like are synonymous and are used in an open-ended manner and do not exclude additional elements, features, acts, operations, and so forth. In addition, the term "or" is used in its broad sense (and not in its exclusive sense), so that the term "or", when used e.g. Used to connect a list of items, one, some or all of the items in the list.

Disjunctive language such as the term "at least one of X, Y, Z", unless expressly stated otherwise, is understood to mean the context generally used to represent that an element, a term, etc. is either X, Y or Z or a combination thereof (eg X, Y and / or Z). Therefore, such disjunctive formulations are generally not intended and should not imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z.

Unless otherwise stated, items such as "a" or "a" are generally to be interpreted as including one or more of the items described. Accordingly, phrases such as "a device configured for" are intended to accommodate one or more recited devices. Such one or more recited devices can also be configured together to perform the specified recitations. For example, "a processor configured to perform recitations A, B and C" may include a first processor configured to perform recitations A and a second processor to perform recitations B and C is configured.

As used herein, the terms "determining" or "determining" may encompass a wide variety of actions. For example, "determining" may include computing, computing, processing, deriving, lookup (e.g., looking up a table, a database, or other data structure), determining, and the like. "Determine" may also include receiving (eg, receiving information), accessing (eg, accessing data in a memory), and the like. "Determine" may also include resolving, selecting, selecting, choosing, setting up, and the like.

The term "selective" as used herein can encompass a variety of actions. For example, a "selective" process may involve determining an option from multiple options. A "selective" process may include one or more dynamically determined inputs, preconfigured inputs, or user-initiated inputs for the determination. In some implementations, an n-input switch may be included to provide selective functionality, where n is the number of inputs used for the selection.

The terms "provisioning" or "deploying" used herein encompass a variety of actions. For example, "providing" may include storing a value at a location for later retrieval, transmitting a value directly to the receiver, transmitting or storing a reference to a value, and the like. The "providing" may also include coding, decoding, encryption, decryption, validation, verification and the like.

The term "message" includes a variety of formats for communicating (e.g., sending or receiving) information. A message can be a machine-readable aggregation of information such as. An XML document, a fixed-field message, a comma-separated message, or the like. A message may, in some implementations, include a signal used to transmit one or more representations of the information. While reciting in the singular, it is understood that a message may be detected, transmitted, stored, received, etc. in several parts.

A "user interface" (also referred to as an interactive user interface, graphical user interface or UI) may refer to a network-based interface that includes data fields and / or other controls for receiving input signals or providing electronic information and / or providing Information for the user in response to received input signals. A user interface can be implemented in whole or in part using technologies such as Hyper-Text Markup Language (HTML), Flash, Java, .NET, Web Services, and Rich Site Summary (RSS). In some implementations, a user interface may be included in a standalone client (eg, thick client, fat client) configured to communicate (eg, send or receive data) in accordance with one or more of the described aspects is.

While the above detailed description has shown, described, and pointed out novel features with respect to various embodiments, it should be understood that various omissions, substitutions, and alterations may be made in the form and details of the illustrated apparatus or algorithms without departing from the spirit of the disclosure departing. As will be appreciated, certain embodiments described herein may be included in a form that does not provide all of the features and advantages described herein since some features may be used or practiced separately from others. The scope of certain embodiments disclosed herein is indicated by the appended claims rather than by the foregoing description. All changes that result from the meaning and equivalence of the claims should be included in their scope.

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• US 14967086 [0004]
• US Pat. No. 14729894 [0061]

Claims (15)

A computer-implemented method comprising: under the control of a computing device that executes certain computer-executable instructions, Identifying a portion of a first image of a first article for presentation in a first display zone of a display area, the portion of the first image correlating to a first area of the display area covered by the first display zone; Identifying a portion of a second image of a second article for presentation in a second display zone of the display area, the portion of the second image correlating to a second area of the display area covered by the second display zone; Causing the presentation of the portion of the first image in the first display zone and presenting the portion of the second image in the second display zone; Detecting an interaction with the first display zone; and Adjusting the image data presented over the first display zone based on the interaction. The computer-implemented method according to Claim 1 wherein the interaction includes an amount of interaction and an interaction direction, and wherein adjusting the image data presented via the first display zone comprises adjusting the portion of the first image of the subject presented in the first display zone based on the amount of interaction and the direction of interaction. The computer-implemented method according to one of Claims 1 or 2 wherein the interaction includes an extent of interaction and an interaction direction, and wherein adjusting the image data presented via the first display zone comprises: determining that the level of interaction exceeds an interaction threshold; Selecting a third image; Identifying a portion of the third image for presentation in the first display zone, wherein the portion of the third image correlates to the first surface of the display area covered by the first display zone; and causing the presentation of the portion of the first image in the first display zone to be replaced by presenting the portion of the third image. The computer-implemented method according to Claim 3 wherein causing the presentation of the portion of the first image to be replaced by the first display zone comprises causing the portion of the first image to be presented from the first display zone as leaving the display area along the direction of interaction, and causing the presentation of the part of the third image takes place as a shift into the display area along the direction of interaction. The computer-implemented method according to Claim 3 wherein selecting the third image comprises: identifying a category for the first article shown in the portion of the first image; Browsing an image data store using the category; and receiving the third image in response to the search in the image data store, wherein the third image shows another article within the category. The computer-implemented method according to Claim 5 further comprising: generating a pseudo-random value; and selecting the third image from a set of images received in response to the search in the image data store using the pseudorandom value. The computer-implemented method according to Claim 5 wherein the browsing of the image data memory comprises communicating a search request over a network to the image data storage, and wherein causing the presentation of the third image includes causing the presentation of a visible artifact for a portion of the article as shown in the portion of the third image , wherein the visible artifact indicates that the third image was received from the image data storage. The computer-implemented method according to one of Claims 1 . 2 . 3 . 4 . 5 . 6 or 7 , further comprising: storing information identifying the portion of the second image presented in the second display zone and information identifying the portion of the first image presented in the first display zone in a session record; Generating a record identifier for the session record; Receiving the record identifier; Retrieving the session record using the record identifier; and causing adjustment to at least one of the first display zone and the second display zone to display, over the display area, the portion of the first image within the first display zone and the portion of the second image within the second display zone. The computer-implemented method according to one of Claims 1 . 2 . 3 . 4 . 5 . 6 . 7 or 8th , further comprising: Receiving horizontal partition information about the display area, wherein the horizontal partition information identifies the first display zone above a horizontal partition and the second display zone below the horizontal partition, the portion of the first image and the portion of the second image using a size of the display area and the horizontal Partition information can be identified. A system comprising: a data store storing particular computer-executable instructions; and a computing device in communication with the data store, the computing device including a processor that executes the specific computer-executable instructions to cause the system to: Identifying a portion of a first image of a first article for presentation in the first zone of a display area, the portion of the first image correlating to a first area of the display area covered by the first zone; Identifying a portion of a second image of a second article for presentation in a second zone of the display area, wherein the portion of the second image correlates to a second area of the display area covered by the second zone; Causing presentation of the portion of the first image in the first zone and presenting the portion of the second image in the second zone; Detecting an interaction with the first zone; and Adjust the image data presented over the first zone based on the interaction. The system after Claim 10 wherein the interaction includes an extent of interaction and an interaction direction, and wherein the processor executes the particular computer-executable instructions to adjust the image data presented via the first display zone by causing the system to base at least the portion of the first image of the subject presented in the first zone on the extent of interaction and the direction of interaction. The system according to one of Claims 10 or 11 wherein the interaction includes an interaction extent and an interaction direction, and wherein the processor executes the particular computer-executable instructions to set the image data presented over the first zone by causing the system to: determine that the interaction extent exceeds an interaction threshold; Selecting a third image; Identifying a portion of the third image for presentation in the first zone, the portion of the third image correlating with the first surface of the display area covered by the first zone; and causing the presentation of the portion of the first image in the first zone to be replaced by presenting the portion of the third image. The system after Claim 12 wherein the processor executes the particular computer-executable instructions to cause the presentation of the portion of the first image to be replaced by the first zone by at least causing the system to abandon the portion of the first image from the first zone of the display area along the direction of interaction, and cause the presentation of the part of the third image in the first zone as a shift into the display area along the direction of interaction. The system according to one of Claims 10 . 11 . 12 or 13 wherein the processor executes the particular computer-executable instructions to further cause the system to at least: store information identifying the portion of the second image presented in the second zone, and information identifying the portion of an image presented in the first zone identify in a session record; Generating a record identifier for the session record; Receiving the record identifier; Retrieving the session record using the record identifier; and causing adjustment to at least one of the first display zone and the second display zone to display, over the display area, the portion of the first image within the first display zone and the portion of the second image within the second display zone. The system according to one of Claims 10 . 11 . 12 . 13 or 14 wherein the processor executes the particular computer-executable instructions to further cause the system to receive at least: receiving horizontal partition information about the display area, wherein the horizontal partition information identifies the first zone above a horizontal partition and the second zone below the horizontal partition the part of the first image and the part of the second image are identified using a size of the display area and the horizontal partition information.

Images