CN107169490A - Object detection method based on color and texture conspicuousness - Google Patents
Object detection method based on color and texture conspicuousness Download PDFInfo
- Publication number
- CN107169490A CN107169490A CN201710328433.3A CN201710328433A CN107169490A CN 107169490 A CN107169490 A CN 107169490A CN 201710328433 A CN201710328433 A CN 201710328433A CN 107169490 A CN107169490 A CN 107169490A
- Authority
- CN
- China
- Prior art keywords
- image
- color
- texture
- spatial distribution
- sheet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of object detection method based on color and texture conspicuousness, small image sheet is first divided the image into obtain the local message of image, calculate with reference to the uniqueness of image sheet color and the compact of spatial distribution and obtain color conspicuousness, image is filtered with carrying out different scale and direction using Gabor filter simultaneously and obtains texture feature vector, then texture difference is calculated to characteristic vector and obtains texture notable figure, finally the two is combined and obtains final notable figure.This method can obtain satisfied result in terms of Detection results and anti-noise ability.
Description
Technical field
Present invention relates particularly to a kind of object detection method based on color and texture conspicuousness.
Background technology
Human eye can easily judge the salient region in image, and notice the pith of image.It is so-called aobvious
Work property region, it can be understood as the main target in image, is that the vision of people in a short period of time can concentrate notice
Into image, some can excite the region of people's interest.Notable figure can be widely applied to answering for many computer vision fields
With.
In the existing notable area's extracting method of image, many methods are the locally or globally calculating based on Pixel-level, mainly
It is the Characteristic Contrast based on pixel and surrounding pixel, have ignored the guidance of well-marked target self information so that testing result is not
It is all preferable.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of object detection method based on color and texture conspicuousness.
Object detection method based on color and texture conspicuousness, comprises the following steps：
S1：RGB color image to input carries out the conversion of color space；
S2：Image block：It is for dimensionImage I, being broken down into a series of sizes isImage sheet；No
Consider the overlap problem of image sheet, then the sum of image sheet is；For any image piece,
It is expressed as vector form, finally give the matrix of an expression image sheet；
S3：Calculate color saliency value：Color-spatial distribution is defined as the spatial distribution differences of fritter and other image blocks, and uses face
Aberration is away from as weight, therefore image blockSpatial distribution be defined as：
；
Wherein,For color weight,Control the intensity of color weight；
Spatial distribution is represented with exponential function：
；
Wherein,It is the color significance value of i-th of image block,It is color peculiarity,Represent the spatial distribution of color, k
Control the proportion shared by spatial distribution；
S4：Calculate texture saliency value：Texture contrast is between defining image block：
；
Wherein,Represent image sheetTexture contrast,、Represent image sheetWithTexture feature vector,
2 norms of vector are represented, the texture conspicuousness of image is thus obtained；
S5：Fusion Features：Using linear fusion method；
；
WithTo meetConstant coefficient.
The beneficial effects of the invention are as follows：
The present invention first divides the image into small image sheet to obtain the local message of image, with reference to the uniqueness of image sheet color
Calculated with the compact of spatial distribution and obtain color conspicuousness, at the same using Gabor filter image is carried out different scale and
Filter to direction and obtain texture feature vector, then calculating texture difference to characteristic vector obtains texture notable figure, finally by two
Person combines and obtains final notable figure.This method can obtain satisfied result in terms of Detection results and anti-noise ability.
Embodiment
The present invention is further elaborated for specific examples below, but not as a limitation of the invention.
Object detection method based on color and texture conspicuousness, comprises the following steps：
S1：RGB color image to input carries out the conversion of color space；
S2：Image block：It is for dimensionImage I, being broken down into a series of sizes isImage sheet；No
Consider the overlap problem of image sheet, then the sum of image sheet is；For any image piece,
It is expressed as vector form, finally give the matrix of an expression image sheet；
S3：Calculate color saliency value：Color-spatial distribution is defined as the spatial distribution differences of fritter and other image blocks, and uses face
Aberration is away from as weight, therefore image blockSpatial distribution be defined as：
；
Wherein,For color weight,Control the intensity of color weight；
Spatial distribution is represented with exponential function：
；
Wherein,It is the color significance value of i-th of image block,It is color peculiarity,Represent the spatial distribution of color, k
Control the proportion shared by spatial distribution；
S4：Calculate texture saliency value：Texture contrast is between defining image block：
；
Wherein,Represent image sheetTexture contrast,、Represent image sheetWithTexture feature vector,
2 norms of vector are represented, the texture conspicuousness of image is thus obtained；
S5：Fusion Features：Using linear fusion method；
；
WithTo meetConstant coefficient.
Claims (1)
1. the object detection method based on color and texture conspicuousness, it is characterised in that comprise the following steps：
S1：RGB color image to input carries out the conversion of color space；
S2：Image block：It is for dimensionImage I, being broken down into a series of sizes isImage sheet；No
Consider the overlap problem of image sheet, then the sum of image sheet is；For any image piece,
It is expressed as vector form, finally give the matrix of an expression image sheet；
S3：Calculate color saliency value：Color-spatial distribution is defined as the spatial distribution differences of fritter and other image blocks, and uses face
Aberration is away from as weight, therefore image blockSpatial distribution be defined as：
；
Wherein,For color weight,Control the intensity of color weight；
Spatial distribution is represented with exponential function：
；
Wherein,It is the color significance value of i-th of image block,It is color peculiarity,Represent the spatial distribution of color, k
Control the proportion shared by spatial distribution；
S4：Calculate texture saliency value：Texture contrast is between defining image block：
；
Wherein,Represent image sheetTexture contrast,、Represent image sheetWithTexture feature vector,
2 norms of vector are represented, the texture conspicuousness of image is thus obtained；
S5：Fusion Features：Using linear fusion method；
；
WithTo meetConstant coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710328433.3A CN107169490A (en) | 2017-05-11 | 2017-05-11 | Object detection method based on color and texture conspicuousness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710328433.3A CN107169490A (en) | 2017-05-11 | 2017-05-11 | Object detection method based on color and texture conspicuousness |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107169490A true CN107169490A (en) | 2017-09-15 |
Family
ID=59814857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710328433.3A Withdrawn CN107169490A (en) | 2017-05-11 | 2017-05-11 | Object detection method based on color and texture conspicuousness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169490A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242854A (en) * | 2018-07-14 | 2019-01-18 | 西北工业大学 | A kind of image significance detection method based on FLIC super-pixel segmentation |
| CN110349131A (en) * | 2019-06-25 | 2019-10-18 | 武汉纺织大学 | A kind of color textile fabric retrochromism detection method |
-
2017
- 2017-05-11 CN CN201710328433.3A patent/CN107169490A/en not_active Withdrawn
Non-Patent Citations (1)
| Title |
|---|
| 丁祖萍 等: ""一种基于颜色和纹理的显著性目标检测算法"", 《计算机工程与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242854A (en) * | 2018-07-14 | 2019-01-18 | 西北工业大学 | A kind of image significance detection method based on FLIC super-pixel segmentation |
| CN110349131A (en) * | 2019-06-25 | 2019-10-18 | 武汉纺织大学 | A kind of color textile fabric retrochromism detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103277B (en) | Gait recognition method based on depth camera and 3D convolutional neural network | |
| CN103914699B (en) | A kind of method of the image enhaucament of the automatic lip gloss based on color space | |
| CN104574366B (en) | A kind of extracting method in the vision significance region based on monocular depth figure | |
| Ginosar et al. | Detecting people in cubist art | |
| EP3218878B1 (en) | Image to item mapping | |
| WO2018119406A4 (en) | Image processing to determine center of balance in a digital image | |
| CN106204690B (en) | Image processing method and device | |
| CN106548165A (en) | A kind of face identification method of the convolutional neural networks weighted based on image block | |
| WO2018082389A1 (en) | Skin colour detection method and apparatus, and terminal | |
| CN104658030B (en) | The method and apparatus of secondary image mixing | |
| Chen et al. | Obstacle detection system for visually impaired people based on stereo vision | |
| CN101996407A (en) | Colour calibration method for multiple cameras | |
| US11354817B2 (en) | Method and system for monocular depth estimation of persons | |
| CN109919030B (en) | Black eye type identification method and device, computer equipment and storage medium | |
| EP3506149A1 (en) | Method, system and computer program product for eye gaze direction estimation | |
| CN108377374A (en) | Method and system for generating depth information related to an image | |
| US10055824B2 (en) | Image correction device, image correction method and storage medium | |
| CN107481206A (en) | MIcrosope image background equalization Processing Algorithm | |
| CN102567969B (en) | Color image edge detection method | |
| CN107169490A (en) | Object detection method based on color and texture conspicuousness | |
| Ghouaiel et al. | Adaptive augmented reality: plasticity of augmentations | |
| Davis et al. | Facial recognition using human visual system algorithms for robotic and UAV platforms | |
| CN109583341B (en) | Method and device for detecting multi-person skeleton key points of image containing portrait | |
| CN108549872A (en) | A kind of vision attention fusion method being suitable for redirecting image quality measure | |
| JP2014191474A (en) | Concentration ratio determination program, concentration ratio determination apparatus and concentration ratio determination method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170915 |