85results about How to "Improve local contrast" patented technology

A local adaptive method is proposed for automatic detection of microaneurysms in a digital ocular fundus image. Multiple subregions of the image are automatically analyzed and adapted to local intensity variation and properties. A priori region and location information about structural features such as vessels, optic disk and hard exudates are incorporated to further improve the detection accuracy. The method effectively improves the specificity of microaneurysms detection, without sacrificing sensitivity. The method may be used in automatic level-one grading of diabetic retinopathy screening.

The invention provides a face detecting and tracking method and a device. The method comprises the steps of inputting a face image or a face video, preprocessing the face image or the face video in an illumination mode, detecting a face by usage of an Ada Boost algorithm, confirming an initial position of the face, and tracking the face by the usage of a Mean Shift algorithm. According to the face detecting and tracking method and the device, a self-adaptation local contrast enhancement method is provided to enhance image detail information in the period of image preprocessing, in order to increase robustness under different illumination conditions, face front samples under different illumination are added to training samples and accuracy of the face detection is increased by adoption of the Ada Boost algorithm in the period of face detection, in order to overcome the defect that using color of the Mean Shift algorithm is single, grads features and local binary pattern length between perpendiculars (LBP) vein features are integrated by adoption of the Mean Shift tracking algorithm in the period of face tracking, wherein the LBP vein features further considers using LBP local variance for expressing change of image contrast information, and accuracy of the face detection and the face tracking is improved.

The invention discloses an adaptive colour image processing method and an adaptive colour image processing system. The method comprises the following steps of: reading an image to be processed; carrying out overall adaptive transformation on the luminance component of the image to be processed through a non-linear inverse S-type function to obtain an overall luminance enhancement image; regulating the local contrast ratio of the overall luminance enhancement image according to the corresponding relation between the central pixel luminance and the neighborhood pixel luminance of the overall luminance enhancement image to obtain a local luminance enhancement image; and carrying out linear colour restoration on the image to be processed according to the ratio between the luminance components of the local luminance enhancement image and the image to be processed to obtain a colour enhancement image. By the method and through the system of the invention, the luminance of the image to be processed can be adaptively regulated; the contrast ratio of a back area and a bright area is enhanced at the same time; the local contrast ratio of the image to be processed can be effectively enhanced; the over-enhancement phenomenon generated at the edge of the image is inhibited; the colour of the image is well kept; and better enhancement effect is achieved.

The invention provides an image processing method and device. The method comprises the following steps of: an obtaining step, a dividing step, an analyzing step, a gamma coefficient assuring step and a gamma correction step, wherein the obtaining step is used for obtaining a pixel number distribution of an image in a brightness space; the dividing step is used for dividing the brightness space into at least three brightness regions; the analyzing step is used for comparing a pixel number containing the brightness space with a pre-set threshold value in the brightness space to assure a light illumination type of the image, aiming to at least one brightness region in at least three brightness regions; the gamma coefficient assuring step is used for assuring the number of gamma coefficients needed by the gamma correction, the size of each gamma coefficient and a defining domain of the gamma correction corresponding each gamma coefficient, based on the light illumination type of the image and the pixel number distribution of the image; and the gamma correction step is used for carrying out the gamma correction on the image, based on the number of the gamma coefficients, the size of each gamma coefficient and the defining domain of the gamma correction corresponding each gamma coefficient.

A gamut mapping operation (910) detects in-gamut areas surrounded on at least two sides by out-of-gamut areas, and (920, 940) provides additional reduction of the subpixel values in the in-gamut areas to regain some of the contrast between the in-gamut and out-of-gamut areas. Other embodiments are also provided.

The invention discloses a mine image enhancement method based on bilateral filtering and a multi-scale Retinex algorithm. The method comprises the steps that 1 image wavelet decomposition is carried out to acquire high frequency and low frequency coefficients of an image; 2 the multi-scale Retinex algorithm and bilateral filtering are carried out on the low frequency coefficient of the image; 3 a soft threshold filtering algorithm is carried out on the high frequency coefficient of the image; 4 a discrete wavelet inverse transform formula is used to acquire an enhanced spatial domain image; and 5 local self-adaptive contrast enhancing is carried out on the enhanced spatial domain image. Compared with the existing enhancement method, the enhancement method provided by the invention has the advantage that based on wavelet transformation, the multi-scale Retinex algorithm and bilateral filtering are combined for processing; self-adaptive contrast enhancing is finally carried out; a processed picture has the advantages of rich detail, being structured and easy identification; and the shortcomings of halo, blurry detail and poor contrast of a result processed by a traditional scheme are overcome.

The invention discloses an image reinforcing method for a security inspection system. The method comprises the steps of: (A) rebuilding and displaying an initial radiation image on a basis of initial data obtained from a detector of the security inspection system; (B) selecting a target area in the displayed initial radiation image; and (C) enhancing the contrast ratio of the selected target area and displaying the enhanced image. With use of the method for partially enhancing the radiation image disclosed by the invention, an operator can partially enhance the contrast ratio of a suspicious area conveniently to highlight the detailed information of an interesting area, so that display effect of the image can be improved.

If a pixel (106) of an image is displayed in a subpixel area (124) which does not contain a primary color needed to display the pixel, and saturated colors are present in or adjacent to the subpixel area, then some of the pixel's luminance is shifted (850) to adjacent subpixel areas on one but not both sides of the pixel to avoid blurring the pixel. Other embodiments are also provided.

The invention relates to an image mist elimination device and a method, in particular to a real-time image enhancing device and a method aiming at image mist and haze elimination under a lower contrast ration condition of a mist condition or a haze condition. The real-time image enhancing device comprises a decoder, a field programmable gate array (FPGA), a storage and an encoder, wherein the decoder is used for decoding video signals and converting the video signals into an image sequence, the FPGA is used for carrying out an enhancement process of a fast Retinex algorithm on the image sequence, the storage is used for storing the image sequence, and the encoder is used for converting the image sequence on which the enhancing process is carried out into the video signals. According to the real-time image enhancing device and the method, large calculating resources and large data storage capacity are not needed, effects of mist and haze elimination can be met, video image details in mist and haze days are enhanced, image visual quality is improved, the requirement of real-time process of hardware can be met at the same time, initial delay is smaller than 40 milliseconds, and original video frame rate is not affected.

Provided is an image processing apparatus that can effectively display an image by using an optimized dynamic range compression technique and a method of processing an image by using the same. The method includes: obtaining a first blurred image and a second blurred image from the input image; estimating illuminance of the input image by combining the first blurred image and the second blurred image; generating a dark region amplified image from the input image; generating a bright region conserved image from the input image; applying weights to the dark region amplified image and the bright region conserved image, respectively, according to the estimated illuminance; and combining the weighted dark region amplified image and the weighted bright region conserved image to generate a final image.

A method for image processing comprising filtration and conversion to a radiometric color image based on an original image. The method gives the processed image high spatial resolution combined with high dynamic resolution. The original image is made available in digital format. Contrast-increasing filtration is performed on the original digital image. The original digital image is converted into a radiometric pseudocolor image based on a chosen color range in which each color corresponds to an absolute measured, radiated or reflected quantity of energy within a certain wavelength band and where the images are represented in a format containing a luminance component. The filtered contrast-increased original image is scaled in terms of the luminance component in the radiometric color image. The luminance component in the radiometric color image is replaced with the scaled, filtered contrast-increased luminance component of the original image.

Provided is an apparatus and method for enhancing an image by optimizing exposure and grayscale. The apparatus includes a component-extracting unit separating luminance signals and color signals from input image signals; a luminance-enhancing unit enhancing the luminance of the luminance signals; and a contrast-enhancing unit dividing the luminance signal having the enhanced luminance into one or more local areas, and enhancing the contrast of the luminance signal having the enhanced luminance for each local area.

The invention discloses an enhanced display method for color high dynamic range image. The enhanced display method for color high dynamic range image comprises the following steps: executing the nonlinearity correction for the RGB image, building the color image brightness model and extracting the brightness information, building color image chroma model and extracting the chroma information, executing the Retinex filtering operation to the brightness, combining the new brightness with the chroma information and reducing into the RGB image. The method selects the suitable brightness and color model for improving the gray level distribution of the result image and effectively reducing the color distortion problem in the result image, the information included in the high dynamic range image is well recovered by the Retinex filtering operation. The enhanced display method for color high dynamic range image is used for the image enhanced processing unit of the digital camera with HDR function, field surveillance camera and other image collecting device and for the transform processing process for displaying high dynamic range image on the low dynamic range device. The brightness and chroma model of the method is simple and practical, the image is displayed in enhanced mode and the color is kept without distortion.

The invention discloses a noncontact type mouse control method based on video sequence recognition, which comprises the following steps: acquiring a video; detecting a human face; pre-treating a human face image; positioning lips; extracting a tongue action feature vector; recognizing the tongue action; and arousing the mouse operation. According to the method, the mouse operation is controlled by utilizing the lip and tongue action recognition, thereby helping the disabled people who lost the hands to control the mouse. By using the method, the head and eyes of an operator can freely act and are not limited, thereby bringing convenience to the daily use of computers. The traditional face detection method which is realized by using an adaptive enhanced AdaBoost algorithm has an image detection rate being 15 frames per second and cannot meet the real-time demand in the image detection field. By adopting a strategy of adjusting the size of the image acquired by a camera in the method, the face detection is realized on the small image, the detection rate is increased and the detection rate can be increased to 25 frames per second.

The invention relates to the technical field of image processing, and concretely relates to an optical fiber cable sheath fracture early warning method. The method comprises the following steps: firstly collecting a cable image, and obtaining a plurality of initial connected domains; obtaining a plurality of defect clusters according to the position relation of the central points of the initial connected domains, judging the initial connected domain which does not belong to the defect cluster as a linear defect; obtaining principal component directions of all initial connected domains in the defect cluster, and screening the initial connected domains in the defect cluster for the first time; on the basis of each defect cluster, according to the increase and decrease sequence of the pixel value sequence of each initial connected domain and the density of the initial connected domains, secondarily screening the initial connected domains in the defect cluster; obtaining a gray level co-occurrence matrix of each initial connected domain in the defect cluster; according to the entropy mean value of the gray-level co-occurrence matrix, screening initial connected domains in the defect cluster for three times; and marking linear defects and defect clusters after three times of screening to obtain defect positions. According to the embodiment of the invention, irregular defects are detected, and the purposes of cable defect detection and early warning are achieved.

An image processing method and apparatus employ wide dynamic range imaging. The image processing method includes: providing a radiance map; decomposing a luminance value of the radiance map into a base layer and a detail layer; generating a weight using a ratio between the luminance value of the radiance map and the base layer; creating a compressed luminance using the base layer, the detail layer, and the weight; and generating a tone-mapped image using a color value of the radiance map, the luminance value of the radiance map, and the compressed luminance value. The image processing method provides a display image with enhanced local contrast and details.

An image contrast enhancement apparatus and method thereof are provided. The image contrast enhancement apparatus includes an image analysis module, a histogram separation unit, and a histogram adjustment unit. The image analysis module statistically analyzes pixels of an original image to produce a plurality of histogram bins and combines the histogram bins into a sub-histogram. The histogram separation unit separates each sub-histogram in every separation level into two sub-histograms in the next separation level, increases or decreases a base width of each sub-histogram such that the respective group density of two sub-histograms corresponding to the same separation point are substantially identical. The histogram adjustment unit re-distributes histogram bins of each sub-histogram or merges a portion of histogram bins of each sub-histogram in every separation level.

A method for spatially-adaptive tone mapping in an image having high dynamic range includes using a computing device to receive an input image from an image sensor comprising a plurality of pixels having pixel locations and determine within the input image a plurality of local size scales, each comprising a neighborhood having substantially constant illumination. The variation in reflectance within each neighborhood is estimated and local contrast within each neighborhood is enhanced. Using the illumination and variation within the contrast-enhanced neighborhoods, the image is remapped to a reduced dynamic range to generate an output image.

Process for the processing of image data which represent the color values of an image, to achieve optimal color reproduction of the image by an image reproduction system, especially by a photographic printer or photolab in response to the image data. In an exemplary embodiment, the image data which represent first positions in a first color space are received. The first positions are transformed into transformation positions which represent positions in a second color space; and the response of the image reproduction system to the image data is modeled with a model image reproduction system such that the model image reproduction system outputs the response as model positions which represent the color values produced by the model image reproductions system in response to the input of the image data as positions in a second color space. Second positions in the second color space can be determined based on the transformation positions and the model positions to determine optimized image data for the control of the image reproduction system.

The invention discloses a license plate location method, which comprises the following steps of: (1) preprocessing an original vehicle image I (x,y) to obtain an enhanced vehicle image I1 (x,y); (2) correcting the color values of points in the vehicle image I1 (x,y) to obtain a corrected vehicle image I2 (x,y); (3) scanning the corrected vehicle image I2 (x,y), and extracting a blue-and-yellow-concentrated region as a license plate candidate region; and (4) checking a license plate region, i.e. judging the size of the current region, accounting the current region as the license plate region if the region is in a set range, and finishing license plate location. With the adoption of the license plate location method disclosed by the invention, the license plates in vehicle images acquired under general conditions can be located, and the license plates in vehicle images photographed under complicated conditions, such as dim light, rain, snow, smoke and the like, can also be located, so that the license plate location method has important practical value in license plate recognition.

The present invention discloses an image tone dynamic adjustment method and apparatus based on a partial block. The method comprises the following steps: firstly, according to a pixel value of a current pixel on an image, obtaining a luminance component value corresponding to the current pixel; obtaining a background luminance value corresponding to the current pixel according to the background area of the current pixel on the image; obtaining an average luminance value corresponding to the current pixel point according to the neighboring area of the current pixel on the image; according to the background luminance value and the average luminance value corresponding to the current pixel, obtaining a pixel gain coefficient corresponding to the current pixel point; and carrying out gain processing on the pixel value of the current pixel by using the pixel gain coefficient corresponding to the current pixel. By virtue of the method disclosed by the present invention, the local contrast ofthe image can be effectively improved and the details of the image can be well preserved, and at the same time, compared with the existing algorithms, the complexity of the algorithm is relatively simple, and image processing efficiency can be improved in a facilitated manner.

In a method to generate a tone-mapped image from a high-dynamic range image (HDR), an input HDR image is converted into a logarithmic domain and a global tone-mapping operator generates a high-resolution gray scale ratio image from the input HDR image. Based at least in part on the high-resolution gray scale ratio image, at least two different gray scale ratio images are generated and are merged together to generate a local multiscale gray scale ratio image that represents a weighted combination of the at least two different gray scale ratio images, each being of a different spatial resolution level. An output tone-mapped image is generated based on the high-resolution gray scale image and the local multiscale gray scale ratio image.

The invention provides a mammary X-ray image enhancement method comprising the steps that a mammary X-ray image is provided; and local normalization is performed on the local part in the mammary X-ray image so that image information corresponding to the local part can be enhanced. Local information is enhanced via local normalization so that implicit local information in the global image can be effectively enhanced, i.e. low intensity lesions can be effectively enhanced. Furthermore, local filtering is adopted after local normalization so that local contrast can be enhanced, adhesion between local objects can be suppressed and adhesion of the lesions and background tissues can be effectively suppressed.