A Compositive Contrast Enhancement Algorithm of IR Image

Contrast enhancement which aims to increase the contrast of an image with low dynamic range, has been widely studied and exploited. In spite of the great success of many contrast enhancement algorithms, they still have difficulty in achieving both global and local contrast enhancement so that some over-enhancement, under-enhancement or even halo artifacts are often produced in complex images. This paper proposes a simple but efficient contrast enhancement method which may achieve both global and local contrast enhancement and perceptually suppress the above-mentioned problems. A cost function integrating global enhancement with local contrast enhancement is firstly constructed to pose image enhancement as an optimization problem. Then, two key steps are involved in solving for an optimal solution, the just-noticeable difference (JND) model is introduced to perceptually determine maximum local gains and neighbouring gray-level difference for local and global contrast enhancement, respectively, and an adaptive parameter regularization method is invoked to further suppress over-enhancement and halo artifacts. The experimental results on many images both qualitatively and quantitatively demonstrate our algorithm can robustly provide better visual quality in global and local contrast compared to a selection of other well-known state-of-the-art algorithms.

This paper proposes a novel algorithm, which enhances the contrast of an input image using spatial information of pixels. The algorithm introduces a new method to compute the spatial entropy of pixels using spatial distribution of pixel gray levels. Different than the conventional methods, this algorithm considers the distribution of spatial locations of gray levels of an image instead of gray-level distribution or joint statistics computed from the gray levels of an image. For each gray level, the corresponding spatial distribution is computed using a histogram of spatial locations of all pixels with the same gray level. Entropy measures are calculated from the spatial distributions of gray levels of an image to create a distribution function, which is further mapped to a uniform distribution function to achieve the final contrast enhancement. The method achieves contrast improvement in the case of low-contrast images; however, it does not alter the image if the image’s contrast is high enough. Thus, it always produces visually pleasing results without distortions. Furthermore, this method is combined with transform domain coefficient weighting to achieve both local and global contrast enhancement at the same time. The level of the local contrast enhancement can be controlled. Several experiments on effects of contrast enhancement are performed. Experimental results show that the proposed algorithms produce better or comparable enhanced images than several state-of-the-art algorithms.

A contrast enhancement framework under uncontrolled environments based on just noticeable difference

AiTR is well developed field of R/D. Nonetheless. a relatively poor under-sampled infrared video may achieve a sharper imagery by smart pre-processing, similar to super-resolution attempts; the difference is in the details. We took a local adaptive contrast enhancement to exploit the pixel intensity correlation, such as smoothness, contrast, and continuity, among neighborhood pixels of variable region sizes, so-called adaptive local contrast enhancement. The final success or failure rate of AiTR will depend on the choice of cost function, such as LMS, etc. In that, we found that a sparse samples do not satisfy the usual underlying Gaussian assumption, of which the Maximum Likelihood, the Bayesian, the Fisher Rao criteria, etc. are usually depending on a priori assumption of dense sampling approaching the Gaussian statistics. Thus, in this paper, we have developed a sparse sampling classifier, called the min-Max classifier for Aided Target Recognition (AiTR), to minimize the intra-class dispersion and at the same to maximize the inter-class separation to select the optimum features vectors. As a standard test case, we choose Petland eigen-faces to benchmark our performance. We apply Szu's lossless divide and conquer theorem solving the NP Complete TSP solution to treat the multiple classes AiTR, in order to achieve min-Max classifier more efficiently than pair-wise SVM classifier.

Low contrast is a frequent challenge in image analysis, especially within medical imaging and highly saturated scenes. To address this issue, we present a nonlinear transformation for local contrast enhancement in digital images. Our method adapts the hyperbolic tangent function using two parameters: one to select the intensity range for modification and another to control the degree of enhancement. This approach outperforms conventional histogram-based techniques such as histogram equalization and specification in local contrast enhancement, without increasing computational cost, and produces smooth, artifact-free results in user-defined regions of interest. In addition, the proposed method was compared with CLAHE in MRIs, showing that, unlike CLAHE, the proposed method does not enhance the noise present in the background of the image. Furthermore, in deep learning contexts where dataset size is often limited, our method could serve as an effective data augmentation tool—generating varied contrast images while preserving anatomical structures, which improves neural network training for brain tumor detection in magnetic resonance imaging. The ability to manipulate local contrast may offer a pathway toward better interpretability of convolutional neural networks, as targeted contrast adjustments allow researchers to probe model sensitivity and enhance the explainability of classification and detection mechanisms.

A small target detection algorithm in infrared image by combining multi-response fusion and local contrast enhancement

In this paper we present a generalized algorithm for unsharp masking of medical images which takes as one of its inputs a high contrast image underwent local adaptive contrast enhancement. Selection of optimal values of the number of histogram bins, processing window size and intensity lower and upper limits in iterative manner is part of applying Contrast Limited Adaptive Histogram Equalization (CLAHE). Experimental results reveal higher quality of the output images both in terms of root mean square contrast and sharpness. Achieved quality, both visually and quantitatively, is compared to that from the Adaptive Histogram Equalization (AHE) algorithm, limited histogram stretching and ordinary histogram equalization which proves its applicability. The algorithm is considered appropriate for processing a number of types of images, such as CT, X-ray, etc.

A scheme for enhancing local contrast of ultrasound images based on multiscale morphology is presented in this paper. The conventional theoretical concept of local contrast enhancement using mathematical morphology has been applied in the field of ultrasound image processing. The main idea is to preserve speckle region unchanged and enhance tissue boundaries. The criterion of speckle region is defined from a similarity value obtained from histogram matching between the histogram in the processing window and a reference one derived from a speckle area. The intensity values of the scale-specific features of tissue boundaries area in the image extracted using multiscale top hat transformation are modified for achieving local contrast enhancement. Locally enhanced features are combined to reconstruct the final enhanced image. The proposed approach has been applied on a set of ultrasound images for testing its response and the result has been compared with that of other standard methods for getting performance.

Histogram equalization, which aims at information maximization, is widely used in different ways to perform contrast enhancement in images. In this paper, an automatic exact histogram specification technique is proposed, and used for global and local contrast enhancement of images. The desired histogram is obtained by first subjecting the image histogram to a modification process and then by maximizing a measure that represents increase in information and decrease in ambiguity. In comparison to a few existing methods, the effectiveness of the proposed automatic exact histogram specification technique in enhancing contrasts of grayscale images is demonstrated through visual assessment of results.

A modular approach on an adaptive thresholding method for segmentation of cell regions in bioelectric images with complex lighting environments and background conditions is presented in this paper. Preprocessing steps involve low-pass filtering of the image and local contrast enhancement. This image is then adaptively thresholded which produces a binary image. The binary image consists of cell regions and the edges of a metal electrode that show up as bright spots. A local region based approach is used to distinguish between cell regions and the metal electrode tip that cause bright spots. Regional properties such as area are used to separate the cell regions from the non-cell regions. Special emphasis is given on the detection of twins and triplet cells with the help of watershed transformation, which might have been lost if form-factor alone were to be used as the geometrical descriptor to sepa rate the cell and the non-cell regions. Keywords: bioelectric images, image segmentation, adaptive thresholding, cell segmentation, local contrast enhancement, watershed transformation, template matching

Contrast and brightness of digital images can be adjusted by contrast enhancement. Mostly digital images are stored in Jpeg format in real application like Internet and Mobile phones. In order to reduce the size digital images are compressed with high, middle and low quality factor. Move and paste type of images are created by malicious person, in which contrast of one source image is enhanced to match the other source image. Detecting global contrast enhancement on previously Jpeg compressed images can identified using global contrast enhancement detection algorithm. Zero height gab bins of histogram used to identify the global contrast enhancement. Zero height gap bins/peaks are used to identify the composite images created by contrast enhancement. Contrast enhancement technique aimed at detecting image tampering has grown in different applications area such as law enforcement, surveillance. Composite detection algorithm and global contrast enhancement detection algorithms are presented here. In order to increase the image processing task parallel approach is used.

A robust segmentation and boundary tracking technique for the extraction of the region and boundary of mammalian cells in bioelectric images is presented. The proposed algorithm consists of four steps. The first step is an image enhancement process composed of low-pass filtering and local contrast enhancement. The second step employs recursive global adaptive thresholding method based on the statistical information of the contrast enhanced image to separate cells and some other image features from the background. Due to the effective image enhancement produced in the previous step, global adaptive thresholding is sufficient to provide satisfactory image thresholding results. The third step in the segmentation process is composed of boundary tracking and morphological measurement for cell detection. A new efficient boundary tracking scheme is proposed. In the last step non-cell objects are found and removed from the segmented image based on the morphological information obtained in the last step.

Image Enhancement works as a first mandatory criteria for an efficient image analysis task. Removing noises and managing the contrast are the two major tasks that need to be accomplished in an image enhancement process. In this article, an innovative approach for color image enhancement is proposed. The proposed approach is a two-step technique. The first step is the noise removal step. Here, an improved median filter, Improved_Median(), is introduced to smooth the noises which exist in the original color image. Then, in the second step, local contrast enhancement is done. For that, an improved version of CLAHE, AA_CLAHE() is proposed for the local contrast management of the filtered image. The V-channel of HSV color space is used for the color computations involved in the local contrast management process. The overall enhancement done by the proposed approach is found to be satisfactory and outperforms the same produced by other state-of-the-art algorithms through experiments on several noisy and poor contrast color images obtained from different standards databases.

The effect of image processing of digital radiographic data on lesion detectability in clinical images has not been systematically studied. In this experiment, we evaluated a low frequency suppression filter program applied to CT digital radiographic localization images (General Electric Scoutview). Three different filter parameters affecting edge enhancement and local image contrast were applied to a set of digital chest images. A standard observer detection experiment comparing the variously filtered digital images and standard chest radiographs in the detection of lung nodules (11 peripheral lung fields, one superimposed on aortic arch) was performed. Standard chest radiography was more sensitive than the digital chest images, although some improvement was noted with increase in local image contrast and edge enhancement. Both image formats were equally specific. Image processing would be better evaluated using a digital imaging system with better performance parameters.

A new approach to design rank-order filters based on an explicit use of spatial relations between image elements is proposed. Many rank-order processing techniques may be implemented by applying the approach, such as noise suppression, local contrast enhancement, and local detail extraction. The performance of the proposed rank-order filters for suppression a strong impulsive noise in a test interferogram-like image is compared to conventional rank- order algorithms. The comparisons are made using a mean square error, a mean absolute error, and a subjective human visual error criteria.