Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing device

An image processing device and image processing technology, which are applied in the directions of image communication, television, instruments, etc., can solve the problems of inability to compensate for the face area and inability to detect multiple face areas at the same time.

Inactive Publication Date: 2009-07-29
PANASONIC CORP
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, for an image in which the face area is overexposed or underexposed due to shooting in a harsh environment such as low illuminance or backlighting, the imaging device of the above-mentioned Japanese Patent Application Laid-Open No. 2007-201963 performs image quality compensation on the entire frame data, Thus, for example in Figure 26A The image 301 showing an overexposed face area and an underexposed face area mixed in the same frame data, such as Figure 26B In the shown image 302 with underexposed face regions mixed at different levels, or with overexposed face regions mixed at different levels, it is not possible to compensate all the face regions contained in the same frame data at the same time, so , cannot detect multiple face regions at the same time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing device
  • Image processing device
  • Image processing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0043]FIG. 1 is a diagram showing the overall configuration of an image processing device and an imaging device according to Embodiment 1 of the present invention. The image processing device 114 in this embodiment includes: an image data memory 101 that stores input image data; and a block data dividing unit that generates image data (block data) for each block obtained by dividing an image based on the image data into a plurality of blocks. 102: Based on the block data information output by the block data division unit 102, the compensation control unit 103 that controls the compensation parameters used to compensate the image quality; uses the compensation parameters determined by the compensation control unit 103 to perform image quality compensation for image quality compensation part 104; and a face region detection part 105 which detects a face region of a person as a specific region in the image data stored in the image data memory 101. The face area detection unit 105...

Embodiment approach 2

[0058] In Embodiment 1 above, since the input image is divided into a certain number, for example, 24 blocks of 6×4, for example, when the input image is Figure 6 In the image shown, the face area cannot be detected with high accuracy. That is, according to Embodiment 1 in which the input image is divided into a certain number of blocks, as Figure 7 As shown, the input image is divided into a total of 24 blocks of, for example, 6×4. Next, the average luminance levels of the blocks 901 to 924 are calculated, and compensation parameters are determined for each block by the compensation control unit 103 .

[0059] exist Figure 7 In the example of , the average brightness levels of the blocks 901 to 924 are: block 901 = 20, block 902 = 90, block 903 = 180, block 904 = 190, block 905 = 120, block 906 = 40, block 907 = 20, Block 908=90, Block 909=180, Block 910=180, Block 911=120, Block 912=30, Block 913=30, Block 914=80, Block 915=160, Block 916=170, Block 917=110, Block 918...

Embodiment approach 3

[0076] In the above-mentioned embodiment 2, since image quality compensation is performed on each rectangular block, for example, in Figure 13 When an image mixed with an underexposed face area and an overexposed face area is input as shown, the face area cannot be detected with high accuracy. That is, according to the second embodiment in which the input image is divided into rectangular blocks and the image quality compensation is performed for each block, the rectangular block division is arbitrarily performed according to the size of the face area assumed by the face area detection unit 105, and the Such as Figure 14 When the shown actual face area size is close to the block size, it is considered that high-accuracy detection is possible, so an example of this case will be described.

[0077] calculate Figure 14 The average luminance level of each block 1601 to 1612 is determined by the compensation control unit 103 as a compensation parameter for each block. exist ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a image processing method, image processing apparatus and a camera device. Because an inputted image is divided into a plurality of blocks, and an image quality thereof is corrected for each of the divided blocks based on information of image data of the respective blocks. Therefore, even in the case where a region where the dark-area-gradation deterioration is generated and a region where the bright-area-gradation deterioration is generated are included in an image, the inputted image is divided so that blocks correspond to the region where the dark-area-gradation deterioration is generated and the region where the bright-area-gradation deterioration is generated, respectively, and then corrected. As a result, the region where the dark-area-gradation deterioration is generated and the region where the bright-area-gradation deterioration is generated can be corrected at the same time.

Description

technical field [0001] The present invention relates to an image processing method, an image processing device, and an imaging device suitable for detecting a specific region such as a face region with high precision even in a shooting environment where underexposure or overexposure occurs due to low illuminance or backlighting. Background technique [0002] In recent years, digital cameras (digital cameras, digital video cameras, mobile phones with cameras, etc.), monitoring cameras, door entry cameras and other imaging devices and image processing devices have become increasingly popular to incorporate face region detection functions. In a digital camera, automatic focus control (AF, Automatic Focus) or automatic exposure compensation (AE, Automatic Exposure) is performed on the detected face area. In addition, in a surveillance camera, the detected face area is stored to Used to identify suspicious persons, etc. [0003] When detecting the face area, a detection method b...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04N5/14H04N5/243G06K9/00G06K9/34
CPCH04N5/217H04N5/23229H04N5/23219H04N23/81H04N23/611H04N23/80
Inventor 宫腰隆一今川和幸
Owner PANASONIC CORP