IMAGE DISPLAY APPARATUS, IMAGE DISPLAY METHOD, AND COMPUTER PROGRAM PRODUCT

• US 20150116349A1
• Filed: 08/07/2014
• Published: 04/30/2015
• Est. Priority Date: 10/31/2013
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Inventors: Hamada, Shinichiro, Osada, Kunio, Mihara, Isao, Tonouchi, Yojiro, Suzuki, Kaoru
• Granted Patent: US 10,296,803 B2
• Time in Patent Office: Days
• US Class Current: 345/619
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/24323 Tree-organised classifiers
• CPC Class Codes: G06F 18/41 Interactive pattern learning with a human teacher
• CPC Class Codes: G06V 10/7788 the supervisor being a human, e.g. interactive learning with a human teacher
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/287 of Kanji, Hiragana or Katakana characters

Abstract

According to an embodiment, an image display apparatus includes a detection unit, a generation unit, and a display control unit. The detection unit detects areas to be focused in an input image. The generation unit generates a sub image by performing correction for improving visibility on an image of the detected area. The correction includes at least one of size correction for adjusting size of the image of the area, color correction for adjusting color of the image of the area, and distortion correction for transforming the image of the area so as to be an image acquired by viewing the image of the area from the front side. The display control unit displays the generated sub image on a display device together with the input image in a form that accompanies a screen representation representing a correspondence relation with the area.

Claims

1. An image display apparatus comprising:

a detection unit configured to detect areas to be focused in an input image;

a generation unit configured to generate a sub image by performing correction for improving visibility on an image of the detected area to be focused, the correction including at least one of size correction for adjusting size of the image of the area to be focused, color correction for adjusting color of the image of the area to be focused, and distortion correction for transforming the image of the area to be focused so as to be an image acquired by viewing the image of the area to be focused from the front side; and

a display control unit configured to display the generated sub image on a display device together with the input image in a form that accompanies a screen representation representing a correspondence relation with the area to be focused.

2. The apparatus according to claim 1, further comprising a recognition unit configured to perform a recognition process on the target included in the area to be focused, wherein

when the recognition process ends, the display control unit further displays a result of the recognition process on the display device in a form that accompanies a screen representation representing the correspondence relation with the sub image.

3. The apparatus according to claim 2, wherein

the recognition unit performs the recognition process on a target included in the area to be focused selected in accordance with a predefined rule among the areas to be focused, and

the display control unit displays a first sub image and a second sub image on the display device in mutually-different forms, the first sub image being generated from an image of the area to be focused that is selected as the target for the recognition process, and the second sub image being generated from an image of the area to be focused that is not selected as the target for the recognition process.

4. The apparatus according to claim 3, wherein, when a first operation designating the first sub image displayed on the display device is performed, the display control unit stops the display of the result of the recognition process that corresponds to the designated first sub image.

5. The apparatus according to claim 4, wherein

the detection unit detects areas to be focused from an input image by using a discriminative model that is trained with training data set, and

when the first operation designating the first sub image displayed on the display device is performed, the designated first sub image is added to the training data set as a negative example, and the discriminative model is retrained.

6. The apparatus according to claim 3, wherein, when a second operation designating the second sub image displayed on the display device is performed, the recognition unit performs the recognition process on a target included in the area to be focused that corresponds to the designated second sub image.

7. The apparatus according to claim 6, wherein

the detection unit detects areas to be focused from an input image by using a discriminative model that is trained with training data set, and

when the second operation designating the second sub image displayed on the display device is performed, the designated second sub image is added to the training data set as a positive example, and the discriminative model is retrained.

8. The apparatus according to claim 1, wherein the display control unit uses, as the screen representation representing the correspondence relation between the sub image and the area to be focused, a screen representation in which the sub image is arranged in proximity of the area to be focused that corresponds to the sub image.

9. The apparatus according to claim 1, wherein the display control unit uses, as the screen representation representing the correspondence relation between the sub image and the area to be focused, a screen representation in which the sub image and the area to be focused that corresponds to the sub image are linked with a line.

10. An image display method performed in an image display apparatus, the method comprising:

detecting areas to be focused in an input image;

generating a sub image by performing correction for improving visibility on an image of the detected area to be focused, the correction including at least one of size correction for adjusting size of the image of the area to be focused, color correction for adjusting color of the image of the area to be focused, and distortion correction for transforming the image of the area to be focused so as to be an image acquired by viewing a target included in the area to be focused from the front side; and

displaying the generated sub image on a display device together with the input image in a form that accompanies a screen representation representing a correspondence relation with the area to be focused.

11. A computer program product comprising a computer-readable medium including computer-executable instructions for displaying an image, the instructions causing the computer to execute:

detecting areas to be focused in an input image;

generating a sub image by performing correction for improving visibility on an image of the detected area to be focused, the correction including at least one of size correction for adjusting size of the image of the area to be focused, color correction for adjusting color of the image of the area to be focused, and distortion correction for transforming the image of the area to be focused so as to be an image acquired by viewing a target included in the area to be focused from the front side; and

displaying the generated sub image on a display device together with the input image in a form that accompanies a screen representation representing a correspondence relation with the area to be focused.