KR101548835B1 - Method, apparatus, and computer program product for overlapped handwriting - Google Patents

Abstract

Embodiments of the present invention are directed to methods, apparatus, and computer program products for use in overlaid handwriting. The method includes displaying at least one segment obtained by segmentation of the overlapping hand tool; Receiving a request to correct the partition; And responsive to the received request, modifying the at least one segment to obtain at least one new segment.

Description

METHOD, APPARATUS, AND COMPUTER PROGRAM PRODUCT FOR OVERLAPPED HANDWRITING FOR < RTI ID = 0.0 >

The present invention relates generally to information processing. More specifically, embodiments of the present invention relate to methods, apparatus and computer program products related to overlapped handwriting.

As is known, handwriting is a natural and convenient mechanism for a user to enter information into electronic devices such as desktop computers, tablet computers, laptop computers, PDAs or cellular phones, for example. In particular, in conjunction with an appropriate character recognition engine, handwriting can be used to input text for various purposes, such as editing or word-processing within an electronic device.

In a handwriting input operation, a user may use a stylus, a pen, or a handwriting tool such as his finger as if writing on normal paper to create a specific writing area on the target device (e.g., writing pad, touch screen or proximity screen screen). Traces (hereinafter referred to as "pen traces") of the writing instrument on the entry area are recorded, and then one or more character recognition engines execute the appropriate character recognition algorithm to generate the recorded pen traces Character. There are already several available recognition algorithms or products based on character recognition, for example, based on structure recognition, statistical models such as Hidden Markov models, neural networks, and the like. Due to its naturalness and convenience, handwriting has been adopted in more and more computer devices, especially in mobile handsets.

Recently, a technique called overlapping handwriting has been proposed, which allows a user to continuously write one or more characters in a single writing area. In this technique, each character entered is superimposed on the previous character as shown in Fig. By using the overlapping handwriters, the user can continuously write without waiting for timeouts for recognition of each character. In this way, multiple characters can be written smoothly at once without breaks, which improves the efficiency of the operation. In addition, as compared with other handwriting solutions in which multiple writing areas are provided to support sequential writing, the handwriting solution requires a relatively small writing area and thus plays a decisive role in limiting the size of the device.

Referring to Figure 1, a high-level schematic diagram illustrating the general process of the overlaying machine is shown. As shown, in the overlapping machine, the pen trace 102, which consists of strokes for at least one character, needs to be divided into at least one segment 104. This process is called segmentation. The recognition engine then converts the one or more segments into recognized characters 106 as output. Conventionally, the partitioning process was performed in the background. In other words, the segments obtained from the original overlapping handler will not be displayed to the user, but will be recognized immediately. Usually, segmentation and recognition are performed concurrently with the support of a particular language model. In this way, the recognition engine provided the most significant character string based on the input pen traces and the corresponding division results. Clearly, the final recognition accuracy is highly dependent on the quality of the partitioning process.

Ideally, the recognized string should be the exact string that the user originally intended to input. Unfortunately, some solutions have been proposed to improve the accuracy of overlapping handwriting recognition, but some errors are inevitable. Both segmentation and recognition have an error problem. In practice, some existing error correction methods such as candidate lists or single character rewriting can be effective when the segmentation is correct but the recognized string is not correct. However, if an error occurs in the partitioning process resulting in an error in the recognized output string, the conventional correction method (e.g., candidate list) is usually useless.

For example, one type of error that is common in partitioning is what is called a one-stroke error, which means that one segment has one additional stroke or one less stroke. According to statistics, among all possible segmentation errors, segmentation errors are dominant. There are also other types of segmentation errors to be described later. If an error occurs in the partition, the final recognition result will be almost inaccurate. In this case, in the past, there has been no way for the user to effectively correct the recognition result, and therefore the user has to rewrite one or more characters, which has a negative effect on the operational efficiency and further on the user experience.

Considering the above-mentioned problems in the present processing method relating to overlapping handwriters, there is a need to provide a method, apparatus, and computer program product for correcting errors in overlapping handwriting recognition caused by erroneous division, in order to overcome the deficiencies Lt; / RTI >

In one aspect, an embodiment of the present invention provides a method for use in an overlay machine. The method includes displaying at least one segment obtained by segmentation of the overlapping hand tool; Receive a request to correct partitioning; And modifying the at least one segment in response to the received request to obtain at least one new segment.

In another aspect, an embodiment of the present invention provides an apparatus for use in an overlay machine. The apparatus includes at least one processor and at least one memory storing a program of computer executable code. At least one of the memory and the computer executable code causes at least the processor, along with the at least one processor, to cause the device to display at least one segment obtained by segmentation of the overlapping hand tool; Receive a request to correct the partition; And to modify at least one segment in response to the received request to obtain at least one new segment.

In yet another aspect, an embodiment of the present invention provides a computer program product comprising at least one computer readable storage medium having embedded therein computer readable program code portions. The computer executable code portion comprising code for causing at least one segment obtained by segmentation of the overlapping hand to be displayed; Code for receiving a request to correct a partition; And code for modifying at least one segment in response to the received request to obtain at least one new segment.

In yet another aspect, an embodiment of the present invention provides an apparatus for use in an overlay machine. The apparatus includes means for causing at least one segment obtained by segmentation of the overlapping machine to be displayed; Means for receiving a request to correct the partition; And means for modifying at least one segment in response to the received request to obtain at least one new segment.

Using embodiments of the present invention, the partitioning result (i.e., at least one segment) can be provided to the user in a modifiable or editable manner, for example, when there is an error in the recognized string. This allows the user to intuitively find errors that exist in the partition. Next, the user can request to correct the split error in an efficient and easy manner, for example, with only a few operations. According to some embodiments of the present invention, it is possible for a user to initiate a correction or correction of the segmentation result using a predefined set of gestures such as dragging, clicking or sway. In response, the modification or correction of the division result will be performed as requested by the user.

As can be appreciated by those skilled in the art, embodiments of the present invention provide a user with a convenient mechanism by which segmentation errors can be interactively corrected, thereby reducing recognition errors caused by erroneous segments Can be corrected. In this way, an efficient solution is provided in which the user can correct the recognition error caused by erroneous segmentation, thereby significantly improving the user experience. Alternatively or additionally, it may be possible for the user to check and correct the division result before performing the recognition. In this way, it can be ensured that errors are removed from the segment to be recognized. In addition, according to some embodiments of the present invention, the user may modify the input by, for example, adding one or more strokes to the current segment at his or her own initiative.

Other features and advantages of embodiments of the present invention will become apparent from the following description of specific embodiments when read in conjunction with the accompanying drawings which illustrate, by way of example, the principles of an embodiment of the invention.

BRIEF DESCRIPTION OF THE DRAWINGS Embodiments of the invention are presented by way of example, the advantages of which are described in more detail below with reference to the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 shows a high-level schematic diagram illustrating the general process of the overlaying machine.
Figure 2 shows a flow diagram of a method for use in an overlay machine in accordance with an embodiment of the present invention.
Figures 3A-3F illustrate a number of gestures and their respective modifications that may be used to request correction of segmentation in accordance with an embodiment of the present invention.
4A and 4B show examples in which a part or segment being operated in accordance with an embodiment of the present invention is highlighted.
Figure 5 shows a schematic diagram of a graphical user interface (GUI) suitable for use in practicing an embodiment of the present invention.
Figure 6 shows a simplified block diagram of an apparatus for use in an overlay machine in accordance with an embodiment of the present invention.
Figure 7 shows a simplified block diagram of an apparatus suitable for use in practicing the embodiments of the present invention.

Embodiments of the present invention provide methods, apparatus, and computer program products for use in overlaid handwriters, and in particular, that allow a user to interactively correct segmentation errors. According to embodiments of the present invention, segments obtained by segmentation of the overlapping hand tool will be displayed to the user in a modifiable or editable manner. In particular, position and time information is available for each portion (i.e., one or more strokes) included in any segment. Thus, the user can select any portion of any segment, and that portion can be modified as desired using, for example, a predefined set of gestures. As a result, the user can effectively correct any division error, thereby correcting the final recognition result. Optionally or additionally, the user may also examine and correct the result of the segmentation before performing the recognition. In this way, there is no error in the segment to be recognized and, as a result, the final recognition accuracy can be increased.

Embodiments of the present invention will be described hereinafter with reference to the drawings. It will be appreciated that although the specific embodiments of the present invention are hereinafter described primarily with reference to Chinese characters, the scope of the present invention is not limited in this regard. Embodiments of the present invention are equally applicable to characters in all languages suitable for overlapping handwriting.

As mentioned above, Figure 1 shows a high-level schematic diagram illustrating the general process of the overlaying machine. In the prior art, the intermediate result of the division is not displayed to the user. In contrast, in accordance with an embodiment of the present invention, this segmentation result, i.e. one or more segments obtained by segmentation of the original nested handwriting, can be presented to the user and modified by the user, will be.

Figure 2 shows a flow diagram of a method for use in an overlay machine in accordance with an embodiment of the present invention. As shown, the method begins at step S205, where at least one segment obtained by segmentation of the overlapping hand tool is displayed to the user. For example, at least one segment is obtained from a segmentation module capable of performing at least one segment by performing a segmentation process on the overlapping handwritten data. It should be appreciated that this segment may be displayed at the request of the user, for example, when attempting to correct an error in a user recognized string. Additionally or alternatively, the segment may be automatically displayed with the last recognized character string. In some embodiments, segments may be displayed through a graphical user interface as shown in FIG. 5, which will be described in detail later.

The segment serves as a basic unit of subsequent character recognition, and therefore ideally, this segment must correspond to a single character, as described above. A segment consists of one or more strokes. As used herein, the term "stroke " refers to a basic element of a character or segment that is no longer divisible.

It should be understood that in step S205 at least one segment is displayed in an editable or editable manner. That is, the user may select and manipulate the entire segment, or one or more strokes of the segment. To do this, location information of the segment strokes is required. This information may be obtained from the preceding partitioning process. As is known in the art, during the segmentation for the user's overlapping hand, the position information of all the strokes included in this segment can be determined for each segment that is the result of segmentation, regardless of the particular algorithm employed . In other words, based on the segmentation process, the position information of each stroke can be obtained for later use, for example, to pick or pick a stroke as will be described later. Therefore, for each point in the pen trace, the segment and stroke (s) to which the point belongs is determinable.

Also, time information of each stroke is available. For example, the time information of the strokes may be obtained by recording the order of writing of the user for a period of time. In fact, when the structure of a segment is complicated, it will be difficult for the user to select a particular stroke from the segment based solely on location information. At this time, the time information of the stroke can be used together with the position information or in combination with the position information in the selection of the stroke. For example, in a preferred embodiment, a time line for a stroke can be drawn under each segment such that a user can select a portion of the timeline, and then, within that segment, This stroke is selected. Other alternatives for selecting strokes or portions based on position and / or time information are equally possible.

It should be appreciated that any present method or method developed in the future can be used to perform the division of overlapping hand, and the position and / or time information of the strokes can be obtained in a different manner accordingly. The scope of the present invention is not limited in this respect.

Next, in step S210, a request to correct the division is received. If the user finds one or more errors in the segment displayed in step S205, the user may be able to initiate a correction request in some manner. Thereafter, in step S215, in response to the request received in step S210, at least one segment is modified so that at least one new segment is obtained. The operation of step S210 and step S215 will now be described in detail.

In a preferred embodiment of the present invention, at step S205, a request may be received via a set of predefined gestures by the user, and modification of the segment may be done accordingly at step S210. Some typical gestures that may be used in a request to correct segmentation are shown in Figures 3A-3F.

Referring to FIG. 3A, in some cases, it is possible for the segmentation process to inappropriately divide a single character's pen trace into one or more discrete segments. For example, as shown in FIG. 3A, one Chinese character that the user intends to input in the overlapping handwriting is "bright ". However, in the split, the pen trace of this single character has been divided into two separate segments: first segment 310 "day" and second segment 312 "month". To correct this, according to some embodiments of the present invention, at step S210 of the method, the user may be required to modify the segmentation in the following manner.

First, a user may click on or near a bounding box of a first segment 310 using a pointing device (pen, stylus, finger, mouse, or the like) (310). Next, the user is allowed to drag the selected first segment 310 to a predefined neighborhood of the second segment 312, i.e., to move the selected first segment from the first segment 310 and the second segment 312 312 is allowed to drag to a position that is less than a predefined threshold distance. In response, the first segment 310 and the second segment 312 are combined into one segment 314 "light" as shown in FIG. 3A. It will be appreciated that the above-described gestures are for illustration only and other gestures are available.

On the other hand, another type of segmentation error is contrary to the situation shown in FIG. 3A, in which the pen traces of two or more separate characters during segmentation are incorrectly combined into a single segment. This example is shown in FIG. 3B. In this example, the user wanted to input two Chinese characters "day" and "month", but the segmentation engine generated a single segment 320 "light". According to an embodiment of the present invention, this error can be corrected by performing re-segmentation on the segment. The user can request re-segmentation by pre-defined gestures on the segment. In some embodiments, the predefined gesture may be, for example, a double click, a long press, or any other suitable gesture. As shown in FIG. 3B, the user may make a predefined gesture (e.g., double click) on segment 320 "light". Subsequently, a re-segmentation is performed in response to the position and time information of the associated strokes, and the segment 320 is divided into a plurality of segments (two segments 322 and 324 in the example shown in Fig. 3B). It is to be understood that a double click is only an illustrative example of a predefined gesture that may be used to request re-segmentation, and that other gestures are also available.

Fig. 3c illustrates a situation similar to that of Fig. 3b, where two or more segments were improperly combined into a single segment during segmentation. However, unlike FIG. 3B, some of the combined segments are quite simple, each of which consists of a small number of strokes (e.g., consisting of only one or two strokes). According to an embodiment of the present invention, rather than calling the partitioning module to perform re-partitioning at this time, the user simply removes the portion described from the segment by dragging that portion into a predefined area, You can also choose something.

As used herein, a "portion" refers to a portion of a segment of one or more strokes. Selection of the part will be done by selecting a stroke, selection of the stroke will be done utilizing position and time information, and position and time information are available from the segmentation process as described above. For example, when an arbitrary point on a stroke is clicked, it can be selected.

Continuing with the example of Figure 3c, upon dragging to the selected and predefined region, the portion being manipulated will be removed from the original segment, and a new segment will be obtained based on that portion. As a result, one segment is divided into two segments, and this procedure will be repeated until the result is correct. Specifically, as shown in FIG. 3C, the pen trace of the Chinese character " person " and the period "." Of the Chinese character were combined into one segment 330 as an error. At this time, the user can first select a stroke of a period, and then drag the selected stroke to an empty space. In response, the stroke "." Will be removed from the combined segment 330 leaving only "person ". Also, a new segment 334 consisting of the dragged portion will be generated. As a result, two independent segments 332 "person" and segment 334 "." Are obtained. It should be understood that although the depicted portion shown in FIG. 3C includes only one stroke, embodiments of the present invention are also applicable to portions composed of a plurality of strokes.

"를 입력하길 원한다. 그러나 사용자의 기입 오류나 분할 오류로 인해 세그먼트(342) "

"과 세그먼트(340) "

"의 순서가 역전되었다. 본 발명의 실시예에 따르면, 사용자는 예컨대 세그먼트를 선택하여 그것을 세그먼트 순열내의 어떤 위치로 드래깅함으로써 세그먼트의 순서를 정정하도록 요구할 수 있다. 그 후, 순열 내에서 이 세그먼트의 순서는 목표 위치에 기반하여 변경될 것이다. 구체적으로, 도 3d에 도시된 바와 같이, 사용자는 세그먼트(340) "

"을 선택하고, 이것을 세그먼트(342) "

"의 다음 위치로 드래그한다. 이에 응답하여, 세그먼트(340)와 세그먼트(342)의 순서는 변경된다. 일부 다른 실시예로, 예컨대 세그먼트를 빈 공간의 어떤 위치로 드래깅하는 것이 세그먼트 순열의 재정렬(re-ordering)을 유발시킬 수도 있다.Other types of segmentation errors are associated with the order of two or more segments. Unlike a single character handwriting, when an overlapping handwriting is utilized, the user typically wants to enter a plurality of characters, such as phrases or phrases, all at once. Therefore, the recognition result must ensure the correct sequence of character sequences, as well as the accuracy of every single character. For example, referring to FIG. 3D,

Quot ;. However, due to a user ' s entry error or segmentation error, segment 342 "

"And segment 340"

In accordance with an embodiment of the present invention, a user may request, for example, to correct the order of a segment by selecting the segment and dragging it to a position within the segment permutation. The order will be changed based on the target position. Specifically, as shown in FIG. 3D,

&Quot; is selected, and the segment 342 "

In some other embodiments, for example, dragging a segment to a position in an empty space may cause reordering of segment permutations (e.g., re-ordering.

"의 하나의 획(하나의 수직 획 또는 "뚫을 곤 부수(ㅣ)(Shu)")이 두 번째 세그먼트(350) "中"에 오류로 할당되었다. 즉, 전술한 것과 같은 단획 오류(one-stroke error)가 이 분할에서 발생했다. 그 결과, 세그먼트(350) "中"은 하나 이상의 획을 갖는 반면, 세그먼트(352) "

"은 하나의 획이 부족하여, 두 세그먼트 모두 인식 오류가 초래될 가능성이 매우 크다. 본 발명의 실시예에 따르면, 사용자는 이러한 분할 오류를 다루기 위해 다음의 방식으로 정정을 요구할 수 있다.Referring now to FIG. 3E, another example of division correction is shown. In this example, segment 352 "

One of the strokes (one vertical stroke or "burrs (Shu)") was assigned as an error in the second segment 350. That is, one- stroke error occurs in this segmentation. As a result, segment "in" 350 has more than one stroke while segment 352 "

"Is very likely to result in a perceptual error in both segments, due to the lack of one stroke. According to an embodiment of the present invention, a user may request correction in the following manner to deal with this segmentation error.

The user is allowed to select a wrongly allocated portion of the first segment (which contains one or more strokes). Then, the misallocated portion of the first segment is dragged to the predefined neighborhood of the second segment to which this portion should belong. In response to this gesture, modifications of the first segment and the second segment are performed, resulting in the selection being removed from the first segment and being added to the second segment based, for example, on the location and time information of the relevant stroke. Specifically, as shown in FIG. 3E, the user selects a vertical stroke in segment 350 and drags it to a predefined neighborhood of segment 352. In this way, two modified new segments 354 and 356 are obtained.

In fact, the most persistent error stroke is known to be a stroke on the "boundary" of two adjacent characters, because these strokes are most likely to be incorrectly allocated to another segment during segmentation. For example, one or more strokes at the beginning of a segment are likely to be assigned to a segment just before this segment. Likewise, one or more strokes at the end of a segment are often assigned to the immediately following segment of the segment. According to an embodiment of the present invention, in order to handle this common situation well, a specific gesture may be provided that allows the user to select the first or last stroke of the character more easily and accurately. An example of such a gesture is sway. For example, strokes at the beginning of a segment can be selected by clicking inside the segment's bounding box and then quickly moving it to the left, while one or more strokes at the end are quickly clicked inside the bounding box And moving it. As described above, given a segment, time information of each stroke is available, so that it is possible to select one or more strokes of the first or last stroke. Of course, other gestures that select the first and / or last stroke of the segment are equally possible. The scope of the present invention is not limited in this respect.

Note that although the segmentation error is shown in FIG. 3E, embodiments of the present invention are also applicable where one or more strokes of a segment are incorrectly assigned to another segment.

Referring to FIG. 3F, according to an embodiment of the present invention, a user is allowed to add one or more strokes to the current segment. Occasionally, one or more strokes of a character may be missed due to a user's write or segmentation error. Therefore, this segment will lack one or more strokes compared to the character that the user originally intended to input. In other cases, the user may want to change the input to his own will. In any case, the user can directly add a portion (i.e., one or more strokes) to any current segment rather than reentering it from the beginning. In response, a new segment may be generated based on the segment and the segment. As shown in FIG. 3F, another segment 362 "large" has been created by adding a stroke to segment 360 "Person", which consists of segment 360 "Person" and a further stroke "1" .

From the foregoing, it can be seen that when requesting segmentation correction, the user is able to select a particular part or segment including one or more strokes. To this end, gestures for partial selection and gestures for segment selection must be clearly different. According to some embodiments of the invention, this difference may be achieved by the duration of the press or click. For example, a short tap or click corresponds to a selection of strokes, while a long tap or click may correspond to a selection of an entire segment. As another example, a user-configurable option or flag may be provided. If this option or flag is set to the first state, the gesture will be interpreted as a partial selection. On the other hand, if the option or flag is set to the second state, the gesture will be used for segment selection. These are just some examples. All other mechanisms can be used for the difference between partial selection and segment full selection.

It should be understood that the gestures described above are configurable. That is, the user can add new gestures, remove gestures, and / or modify current gestures according to the user's preferences and / or the state of the device. Alternatively or additionally, various parameters related to the gesture, such as the predefined proximity distance (threshold distance), the predefined region and / or the predefined position described above, etc., can also be configured by the user.

Further, as can be appreciated by those skilled in the art, FIGS. 3A through 3E illustrate non-limiting examples of some examples and gestures and their corresponding actions in conjunction with divisional correction only in accordance with embodiments of the present invention . In view of the foregoing, one skilled in the art will readily anticipate other gestures that require division correction. Also, an interaction means that something other than a gesture can be used to request division correction. For example, control means such as buttons, soft keys and drop-down lists may be used alone or in combination to input a correction request. As another example, the user may directly enter certain predefined commands to initiate such a request. The scope of the present invention is not limited in this regard.

Returning to Fig. 2, in step S220, the portion or segment being manipulated is highlighted during modification. By highlighting the element being manipulated, the user can always recognize the focus of the interaction and avoid confusion during modification. Highlighting can be done in many different ways. For example, the color, appearance, shade, font and / or size of the element being manipulated can be changed. Alternatively or additionally, an animation effect may be applied to the portion or segment being manipulated.

4A and 4B, examples according to an embodiment of the present invention are shown, wherein a portion or segment being manipulated is highlighted by a fish eye lens. In the example shown, when the user initiates an operation for a particular portion (FIG. 4A) or segment (FIG. 4B), this portion or segment being manipulated will be displayed in the Fish Eye. The fisheye will be moved during the corrective action, for example, according to the part to be manipulated or the movement of the segment. In addition to the location, the content displayed inside the fishbone may be updated manually or in operation. For example, in the example shown in FIG. 3E, if the user first selects a stroke of the segment 350, the segment 350 and the selected stroke are included in the fisheye, possibly changing the color of the selected stroke. While dragging towards segment 352, segment 350 may be highlighted in the fishery. Finally, when the stroke and segment 352 are combined, that final segment will be displayed in the fisheye. It is to be understood that the fisheye is merely an illustrative example and that one or more highlight effects (e.g., color changes as shown in Figures 4A and 4B) may be used in conjunction.

It should be noted that step S220 is optional since the user can choose to enable / disable the highlight of the element being operated. Also, the highlight effect is configurable. That is, the user may be able to add new effects, remove current effects, and / or configure various related parameters depending on his or her preference or status of the device.

Next, in step S225, the at least one new segment obtained in step S215 is recognized, and one or more characters are output. Thereafter, the method 200 ends. As described above, any currently existing or later developed recognition method may be employed to convert a segment to a letter, and the scope of the present invention is not limited in this regard. Still further, step S225 is selectable because, in some applications, a segment representing the user's original pen trace may be stored and used immediately without recognition. An example of such an application is a writing practice application.

Figure 5 illustrates a graphical user interface (GUI) suitable for use in practicing the embodiments of the present invention. According to some embodiments of the present invention, the GUI 500 may be used in conjunction with the present method 200 and will be generated and provided by, for example, the apparatus described below with reference to Figures 6 and 7.

As shown, the GUI 500 includes an editing area 505, a candidate character area 510, a division result area 515, a writing area 520, and a control area 525. [ In operation, the user may write a plurality of characters in the writing area 520 in an overlapping manner. Next, segmentation and recognition of the user's handwriting will be performed. The final character will be displayed in the editing area 505, and the candidate list will be displayed in the candidate character area 510. Specifically, according to an embodiment of the present invention, the final one or more segments will be displayed in the segmentation result area 515. For example, when the user finds a recognition error caused by an erroneous segmentation, the user can use the segmentation result area 515 and the reciprocal relationship (e.g., Will work. After correction, when the user is sure that there is no error in the segmentation, the segment will be submitted for recognition. Thereafter, the editing area 505 and the candidate character area 510 will be updated accordingly. Alternatively or additionally, it is also possible for the user to inspect and correct the division result displayed in the division result area 515 before executing the recognition. The control area 525 is provided with one or more control means, such as buttons, soft keys or other suitable control means, by which the user will control the processing of the superimposed handwriting.

It should be understood that the GUI 500 shown in Fig. 5 is merely an illustrative example. A GUI suitable for use in practicing the embodiments of the present invention may have fewer or more components and / or may have different components. Optionally or additionally, the layout or arrangement of the GUI may be changed in other embodiments.

Figure 6 shows a simplified block diagram of an apparatus for use in an overlapping machine in accordance with an embodiment of the present invention. As described above, the device 600 will generate and provide a GUI, such as the GUI 500 shown in FIG. 6, the apparatus 600 includes a correction request means 610, a segment modification means 615, a modification highlight processing means 620 (optional), and a character recognition means 625 (optional) .

The segmented display means 605 will be configured to cause display of at least one segment resulting from segmentation of the overlapping handwriters. The correction request means 610 is configured to receive a request to correct the partition. Segment modification means 615 may be configured to modify at least one segment in response to a received request to obtain at least one new segment.

Specifically, the segment modification means 615 is configured to perform one or more of the following operations: in response to dragging the first segment to a predefined neighborhood of the second segment, Into a single segment; Performing a re-segmentation of the first segment to obtain two or more segments in response to a predefined gesture for the portion of the first segment; Removing the portion in the first segment and creating a new segment based on the portion in response to dragging the portion of the first segment to the predefined region; Changing the order of the first segment within the permutation in response to dragging the first segment to a position within the segment permutation; Removing the portion in the first segment and adding the portion to the second segment in response to dragging a portion of the first segment to a predefined neighborhood of the second segment; In response to adding the portion to the first segment, generating a new segment consisting of the first segment and the added portion to replace the first segment.

During operation of the segment modification means 615, the modification highlight processing means 620 is configured to highlight the portion or segment being operated. The character recognition means 625 is configured to perform recognition in cooperation with the segment modification means 615 to convert the corrected segment into editable characters.

It is noted that device 600 may be implemented in hardware or in dedicated circuitry, software, logic, or any combination thereof. Accordingly, various means of apparatus 600 may be implemented as software modules and / or hardware blocks, units, or components.

The implementation of the above-described process or method (e.g., method 200 shown in FIG. 2) may be implemented by any suitable device. Figure 7 shows a simplified block diagram of an apparatus 700 suitable for use in practicing the embodiments of the present invention. In some embodiments, device 700 may be implemented as a mobile terminal. It should be understood, however, that the mobile terminal is merely an example of one type of device that may benefit from embodiments of the present invention, and therefore should not be construed as limiting the scope of embodiments of the present invention.

Apparatus 700 includes an antenna 712 (or multiple antennas) in operable communication with a transmitter 714 and a receiver 716. Apparatus 700 also includes at least one processor or controller 720. The controller 720 includes circuitry necessary to implement the logic functions of the device 700 and the superposition handler. For example, the controller 720 may be comprised of a digital signal processing device, a microprocessor device, various analog-to-digital converters and digital-to-analog converters, and other support circuits. The control and information processing functions of the device 700 are allocated among these devices in view of their respective capabilities.

The device 700 also includes an output device such as an earphone or speaker 724, a ringer 722, a microphone 726, a display 728 and a user input interface, all of which are connected to the controller 720. The user input interface may include any of a number of devices, such as a keypad or keyboard 730, a writer 731, or other input device, that allow the device 700 to receive data. For example, the writing device 731 may include, but is not limited to, a touch screen, a proximity screen, a writing pad, and the like. Specifically, the writing device 731 can receive a superimposed handwriting input by the user. In this regard, the writing device 731 includes all hardware, software, and / or firmware necessary to support the overlapping handwriting.

Additionally or alternatively, the device 700 may include an interface device such as a joystick or other user input interface. The apparatus 700 also includes a battery 734, such as a vibrating battery pack, for example, which provides mechanical vibration as a detectable output, as well as powering various circuits needed to operate the apparatus 700.

In some embodiments, the apparatus 700 includes a media capturing element such as a camera, video and / or audio module that communicates with the controller 720. Media capturing elements are any means of capturing images, video and / or audio for storage, display or transmission. For example, in an exemplary embodiment in which the media capturing element is a camera module 736, the camera module 736 may include a digital camera capable of forming a digital image file from the captured image. When implemented in a mobile terminal, the device 700 may also include a universal identity module (UIM) The UIM 738 is typically a memory device having an embedded processor. UIM 738 may include, for example, a subscriber identity module (SIM), a general purpose IC card (UICC), a universal subscriber identity module (USIM), a removable user identification module (R-UIM) The UIM 738 typically stores information elements associated with a subscriber.

Apparatus 700 will be mounted with at least one memory. For example, the device 700 may include a volatile memory 740 such as a RAM that includes a cache area for temporary storage of data. Apparatus 700 may also include other non-volatile memory 742, which may be embedded and / or removable. Nonvolatile memory 742 may additionally or alternatively include EEPROM, flash memory, and the like. The memory may store a plurality of information, programs, and data used by the device 700 to implement the functionality of the device 700. For example, the memory may store a program comprised of computer executable code that may be configured to cause the device 700, along with the controller 720, to perform at least the steps of the method 200 described above.

Embodiments of the present invention may be implemented as a computer program product including at least one computer readable storage medium having embedded therein computer readable program code portions. In this embodiment, the computer readable program code portion comprises at least one code for performing the steps of the method 200 described above.

In order to illustrate the principles of the invention, some specific embodiments have been described. As described above, embodiments of the present invention provide methods, apparatus, and computer program products for use in overlaid handwriters, and more particularly, to methods, apparatus, and computer program products that enable a user to interactively correct segmentation errors to provide. According to an embodiment of the present invention, the segments obtained by the superimposing unit, which is an input by the user, may be displayed in a modifiable or editable manner. In particular, position information and time information (writing order) associated with each part (or stroke) contained within each segment is available so that the user can select any part of any segment, The desired part can be modified using the gesture set. As a result, the user is provided with an efficient and convenient method by which the overlapping handwriting recognition result can be corrected. Alternatively or additionally, the user may choose to check and correct the segmentation results before performing the recognition, thereby ensuring that the segment recognized is error-free. In fact, the correction of the division can be performed before, simultaneously with, or after the recognition of the character, and the scope of the present invention is not limited in this respect.

Experiments show that using the embodiment of the present invention, the efficiency of correcting overlapped handwriting-related recognition errors caused by division errors is increased compared to the conventional overlay handwriting solutions. In addition, the user has no need to rewrite one or more characters in the case of recognition errors, thus improving user experience and satisfaction.

In general, the various illustrative embodiments may be implemented in hardware or in dedicated circuitry, software, logic, or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor or other computing device, and the invention is not limited in this regard. While various aspects of the exemplary embodiments of the present invention have been described using block diagrams, flowcharts, or other pictorial representations, it should be understood that such blocks, devices, systems, techniques or methods described herein may be implemented in hardware, , Dedicated circuitry or logic, general purpose hardware or controller, or other computing device, or some combination thereof.

The various blocks shown in FIG. 2 may be referred to as a plurality of connected circuit elements that may be referred to as method steps and / or operations resulting from the operation of computer program code, or may be configured to perform a related function. At least some aspects of an exemplary embodiment of the present invention may be implemented with various components such as, for example, IC chips and modules, and the exemplary embodiments of the present invention may be realized with an apparatus embodied in an integrated circuit. The integrated circuit (s) may include circuits implemented as at least one of a data processor (s), a digital signal processor (s), a baseband circuit, and a radio frequency circuit configured to operate in accordance with an exemplary embodiment of the present invention If available, with firmware).

Various modifications and variations of the above-described exemplary embodiments of the present invention will become apparent to those skilled in the art from the foregoing description, when read in conjunction with the accompanying drawings. Any and all modifications will fall within the scope of the non-limiting and exemplary embodiments of the invention. Further, it will be understood by those skilled in the art that other embodiments of the invention set forth herein may have the benefit of the teachings presented in the foregoing descriptions and the associated drawings.

It is, therefore, to be understood that the embodiments of the invention are not limited to the specific embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, these terms are used in a generic and descriptive sense only and not for purposes of limitation.

Claims (37)

delete delete delete delete A method for use in an overlapping machine,
Displaying at least one segment obtained by segmentation of the overlapping hand tool,
Receiving a request to correct the partition;
And modifying the first one of the at least one segment in response to the received request to obtain at least one new segment,
The above-
In response to dragging a portion of the first segment to a predefined region, removing the portion from the first segment and creating a new segment based on the portion
Way.
delete delete delete delete A method for use in an overlapping machine,
Displaying at least one segment obtained by segmentation of the overlapping hand tool,
Receiving a request to correct the partition;
And modifying the first one of the at least one segment in response to the received request to obtain at least one new segment,
The above-
In response to adding a portion to the first segment, creating a new segment comprising the first segment and the added portion to replace the first segment
Way.
11. The method according to claim 5 or 10,
During the modification, further comprising highlighting the portion or segment being manipulated
Way.
11. The method according to claim 5 or 10,
And recognizing the acquired at least one new segment as at least one character
Way.

delete delete delete delete An apparatus for use in an overlaying machine,
At least one processor,
At least one memory for storing a program of computer executable code,
Wherein the at least one memory and the computer executable code are configured to cause the device, along with the at least one processor,
Display at least one segment obtained by segmentation of the overlapping hand tool,
Receive a request to correct the partition,
And to modify the first one of the at least one segment to obtain at least one new segment in response to the received request,
The above-
In response to dragging a portion of the first segment to a predefined region, removing the portion from the first segment and creating a new segment based on the portion
Device.
delete delete delete delete An apparatus for use in an overlaying machine,
At least one processor,
At least one memory for storing a program of computer executable code,
Wherein the at least one memory and the computer executable code are configured to cause the device, along with the at least one processor,
Display at least one segment obtained by segmentation of the overlapping hand tool,
Receive a request to correct the partition,
And to modify the first one of the at least one segment to obtain at least one new segment in response to the received request,
The above-
In response to adding a portion to the first segment, creating a new segment comprising the first segment and the added portion to replace the first segment
Device.
The method according to claim 17 or claim 22,
Wherein the at least one memory and the computer executable code are configured to cause the device, along with the at least one processor,
During the modification, it is further configured to highlight the portion or segment being manipulated
Device.
The method according to claim 17 or claim 22,
Wherein the at least one memory and the computer executable code are configured to cause the device, along with the at least one processor,
And to recognize the acquired at least one new segment as at least one character
Device.
delete delete delete delete A computer readable storage medium having embedded therein computer readable program code portions,
The computer readable program code portion comprising:
Code for displaying at least one segment obtained by segmentation of the overlapping hand tool,
A code for receiving a request to correct the partition;
And code for obtaining at least one new segment by modifying the at least one segment in response to the received request,
The obtaining code includes:
In response to dragging a portion of the first segment to a predefined region, removing the portion from the first segment and generating a new segment based on the portion
Computer readable storage medium.
delete delete delete delete A computer readable storage medium having embedded therein computer readable program code portions,
The computer readable program code portion comprising:
Code for displaying at least one segment obtained by segmentation of the overlapping hand tool,
A code for receiving a request to correct the partition;
And code for obtaining at least one new segment by modifying the at least one segment in response to the received request,
The obtaining code includes:
In response to adding a portion to the first segment, generating code to create a new segment of the first segment and the added portion to replace the first segment
Computer readable storage medium.
35. The method of claim 29 or 34,
The computer readable program code portion comprising:
Further comprising code for highlighting the portion or segment being manipulated during said modification
Computer readable storage medium.
35. The method of claim 29 or 34,
The computer readable program code portion comprising:
Further comprising code for recognizing the acquired at least one new segment as at least one character
Computer readable storage medium. delete

Images