TWM584676U - Digital aid - Google Patents

Abstract

A digital assistive device includes a camera lens, a computing device, and a sound generating device. The camera lens is suitable for capturing an image. The computing device is connected to the camera lens, receives the image and recognizes the image, and generates an image recognition result. The sound generating device is connected to the computing device, and receives and plays the image recognition result.

Description

Digital aids

An assistive device, especially a digital assistive device

Physically impaired people often have many inconveniences due to physical defects. Therefore, a variety of assistive devices are also needed to assist the lives of people with physical disabilities. From simple guides to more technical hearing aids.

However, most of the assistive devices have a single function and mostly assist users in a simple way. In fact, half of the assistive devices have not been given complete assistance, and it is still impossible for users to effectively overcome their obstacles. For example, a guide stick identifies obstacles in the front through collisions, but cannot identify the type of obstacles in front, or even whether it is another person.

In recent years, with the advancement of science and technology, many functions can provide more assistance to users through digital technology practice when applied to assistive devices, and users outside the disabled can also provide a lot of assistance. There are currently few applications for digitizing assistive devices. Therefore, how to make the assistive device provide more auxiliary functions through digital technology is worth thinking about by those with ordinary knowledge in the field.

This creation provides a digital assistive device that analyzes the image content using a camera lens and image recognition technology to provide visual aids.

This creation provides a digital aid, including a camera lens, a computing device, and a sound device. The camera lens is suitable for capturing an image. The computing device is connected to the camera lens, receives the image and recognizes the image, and generates an image recognition result. The sound generating device is connected to the computing device, and receives and plays the image recognition result.

In the above digital assistive device, the sound generating device is an earphone device.

The aforementioned digital aids further include a wearing accessory, and the camera lens is disposed on the wearing accessory.

The above digital aids further include an augmented reality module disposed on the wearable accessory, and the augmented reality module is connected to the computing device, and the augmented reality module is suitable for displaying The image recognition result.

In the above digital aids, the computing device recognizes the image through item recognition, face recognition and text recognition.

In the above digital aid, the computing device further includes a storage module, which is suitable for storing a plurality of personal data.

The above digital aids, wherein the computing device further includes a control interface.

100‧‧‧ digital aids

110‧‧‧ Computing Device

120‧‧‧ sounding device

130‧‧‧ camera lens

140, 240‧‧‧ Wearable accessories

241‧‧‧AR lens

S01 ~ S12‧‧‧Flowchart steps

Figure 1 shows the digital aids for this creation.

FIG. 2 illustrates an image recognition process of a computing device.

FIG. 3 illustrates a digital assistive device according to another embodiment.

This creation provides a digital assistive device that uses a camera lens and image recognition technology to assist users by playing the recognition results through sound.

Please refer to FIG. 1. FIG. 1 illustrates the digital assistive device for this creation. The digital assistive device 100 includes a computing device 110, a camera lens 130, a sound emitting device 120, and a wearing accessory 140. The camera lens 130 is a device capable of capturing images. And the camera lens 130 is adapted to capture an image. In this embodiment, the camera lens 130 is a high-definition lens for capturing clear images, and the camera lens 130 is disposed on the wearing accessory 140 so that it is convenient for users to wear and carry.

The sound generating device 120 is a device capable of emitting sound. In this embodiment, the sound generating device is an earphone, and in some embodiments, it can also be provided as a device such as a hearing aid. The sound generating device 120 is connected to the computing device 130. The preferred embodiment is connected to the computing device 110 by a wired method. The sound generating device 120 is adapted to play sound information from the computing device 110.

The wearing accessory 140 is an object suitable for users to wear. In this embodiment, the wearing accessory 140 is a pair of glasses, but it is not limited to this. The wearing accessory can also be designed as other types of accessories, such as necklaces, neck rings, Bracelets, pins, buckles, smart clothes, etc., as long as they can be worn by the user. The wearable accessory 140 is a digital aid, and the wearable accessory 140 is used to carry the camera lens 130. For example, in the embodiment of FIG. 1, the camera lens 130 is disposed on the frame of the glasses 140 and shoots along the line of sight of the wearer.

The computing device 110 is a computing core of the digital assist device 100 and is provided with a processor. In addition, the computing device 110 is connected to the camera lens 130 and the sound emitting device 120, respectively, and is connected through a wire. In this embodiment, the computing device 110 further includes a storage module that stores the operating system of the computing device 110, and is further suitable for storing data required for image recognition, such as facial data of a person and corresponding personnel. Name and more. In addition, in some embodiments, the computing device 110 is a smart phone, and the computing function of the digital assistant 100 is installed in the smart phone in the form of APP software.

The computing device 110 receives an image from the camera lens 130. The image is recognized, and an image recognition result is generated. In this embodiment, the computing device 110 recognizes an image through techniques such as item recognition, face recognition, and text recognition. Further, the article identification uses SSD (Single Shot Detector) technology for image recognition to achieve the effect of item identification. The article identification is to identify objects appearing in the image, such as steps, street lights, power poles and other objects.

Face recognition uses ResNet-10 as the main recognition technology, so people can be identified from the image through face recognition technology. Further, the result of the face recognition may correspond to the person data in the storage module of the computing device 110 to determine the identity of the person in the image.

Text recognition is the basis of text recognition using Tesseract. In addition to interpreting text, it can also analyze the semantics produced by text arrangement. Further, the determined semantic meaning is converted into speech through TTS (Text to Speech) technology.

Please refer to FIG. 2, which illustrates an image recognition process of a computing device. First, at the beginning (step S01), the camera lens 130 will be focused (step S02). In a preferred embodiment, the object is focused at a distance of 3 meters. Next, it is judged whether the object is a person (step S03). If the object is a person, the person is identified (step S04), and if the object is not a person, the object or text is identified (step S08).

When step S04 is performed, the computing device 110 recognizes whether the character is a preset character according to the condition 111, that is, whether it corresponds to the personnel data in the storage module. If it is a known person (step S05), the voice is played (step S12). If the person is an unknown person (step S06), the recognition of the item or character is performed (step S08).

When recognizing an item or text (step S07), the computing device 110 recognizes whether the object has clear text according to the condition 112. If there is clear text on the object, determine whether the file is offset (step S09), if the file is offset, play a voice prompt to correct the lens (step S11), and continue to judge the file Whether to offset. If the file is not shifted, character recognition is performed (step S10), and after the character recognition is completed, voice playback is performed (step S12). When step S07 is performed, if the object does not have clear text, the article is identified (S08). After the article is identified, the voice is played (step S12).

Through the above-mentioned item recognition, face recognition and text recognition, the computing device 110 can judge the image, and the computing device 110 generates an image recognition result. The image recognition result includes the above-mentioned item recognition result, face recognition result and text recognition result. . The computing device converts these image recognition results into sound files and plays them through the sound generating device 120.

In addition, in one embodiment, the computing device 110 further includes a control interface. The control interface is suitable for inputting control instructions to the computing device, such as various settings, creating or editing personnel data, and the like. The control interface can be designed to be installed on the computing device 110, and can also be designed as an external control interface. For example, the computing device 110 is connected to the computing device 110 wirelessly (Bluetooth or NFC) or wired.

Please refer to FIG. 3. FIG. 3 illustrates a digital assistive device according to another embodiment. In the embodiment of FIG. 3, the digital assistive device 200 includes a computing device 110, a camera lens 130, a sound emitting device 120, and a wearing accessory 240. The camera lens 130 and the sound generating device 120 are similar to the foregoing embodiments, and are not repeated here. In this embodiment, the wearable accessory 240 further includes an augmented reality module. The wearable accessory 240 is connected to the computing device 110, and the augmented reality module recognizes the display image recognition result. Therefore, in this embodiment, the wearing accessory 240 is an augmented reality glasses (AR glasses), and the computing device 110 also recognizes that the image recognition result is converted into augmented reality information, and is projected on the AR through the wearing accessory 240 On the lens 241. For example, when image recognition is performed, the AR lens 241 projects a line drawing of the appearance of the object projected by the projection object. When the recognition is completed, the recognition result can be projected on the AR lens 241, and the image recognition result is displayed according to the position of the object, such as the face recognition is completed, and relevant data such as name, identity, etc. are displayed directly next to the person To help users determine who they are.

The digital assistive device 100 of the present invention captures an image through the camera lens 130, analyzes the image captured by the camera lens 130 through the computing device 110, determines the image content through image recognition technology, and then notifies the user through voice playback to assist the user in Visual impairments, especially for visually impaired people, identify the surrounding environment and are simple to use and easy to use.

The present invention is explained above by way of examples, but it is not intended to limit the scope of patent rights claimed by the present invention. The scope of its patent protection shall depend on the scope of the attached patent application and its equivalent fields. Anyone with ordinary knowledge in the field, without departing from the spirit or scope of this patent, makes changes or retouches that are equivalent changes or designs made under the spirit disclosed in this creation, and should be included in the scope of patent application described below Inside.

Claims (7)

A digital assistive device includes: a camera lens adapted to capture an image; a computing device connected to the camera lens, receiving the image and recognizing the image to generate an image recognition result; and a sound emitting device connected to the The computing device receives and plays the image recognition result. The digital assistive device according to item 1 of the scope of patent application, wherein the sound generating device is an earphone device. The digital assistive device described in item 1 of the patent application scope further includes a wearable accessory, and the camera lens is disposed on the wearable accessory. The digital assistive device described in item 3 of the scope of patent application, further comprising an augmented reality module set on the wearable accessory, and the augmented reality module is connected to the computing device, and the expansion device The augmented reality module is adapted to display the image recognition result. The digital assistive device described in item 1 of the scope of patent application, wherein the computing device recognizes the image through item recognition, face recognition and text recognition. According to the digital assistive device described in item 1 of the scope of patent application, wherein the computing device further includes a storage module, which is suitable for storing a plurality of personal data. The digital assistive device described in item 1 of the scope of patent application, wherein the computing device further includes a control interface.