An efficient enhanced automatic target recognition approach

An important aspect of 2D object recognition is matching. Based on a generalized distance transform method, Borgefors introduced the concept of the Chamfer scheme to 2D object matching. In Chamfer matching, a successful match is obtained when a scene in a reference image is correctly matched to the corresponding scene in the target image. The successful match corresponds to the lowest matching measure computed from the sum of Chamfer distances. However, if the target image has not been correctly corrected for distortions, there may not be an ideal best fit between the reference and target images. Instead, matching measures corresponding to local minima exist, for which it is difficult to choose the correct matching measure that corresponds to the best fit. The match fit corresponding to the global minimum measure may not necessarily be the best fit as there are many sub-optimal measures that could provide equally good fits between the target and reference images. This paper advocates that aside from the Chamfer matching measure, additional considerations need to be factored in to improve on finding the true global minimum measure which corresponds to the optimal fit. Int his paper, a new method has been designed to find the optimal fit between poorly-rectified target and reference images. The new approach uses simulated annealing to improve on the matching results. Simulated annealing is a powerful stochastic optimization technique for nonlinear problems. In our novel technique, the energy function for simulated annealing comprises two terms: a smoothness constraint term and the Chamfer matching measure term. The high computational burden of simulated annealing is reduced by using edge information for the matching process. Results are presented to illustrate the new matching technique.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

It is very challenging task to retrieve accurate image from huge digital images due to which much interest has been gain by CBIR. Feature based methods are prove to be more efficient as compared to text based query methods. As in case of CBIR a similarity between already stored database images and query by user can be extracted through shape, texture, color and structure like low level primitive features. This paper gives the idea about use of image retrieval in various fields and gives the problem related to Image retrieval. Its main problem is the retrieval of user requested images and search from database. A typical CBIR system automatically extracts shape, spatial, texture and colors information like visual attributes of every image in database. These extracted pixel values are stored in a different database within the system is called a feature database. There is increase in number of CBIR systems that result in increase of classification of these systems. One way of classifying these systems are texture, shape, colour and most frequently used features for feature extraction phase of CBIR systems. In last we review various works done by researchers in CBIR classification using Convolution neural network, Support vector machine, Random forest, Decision tree and K-nearest neighbour. This helps user in identifying the use of best classifier according to user need.

The iris is a part of the human anatomy that can be used as a biometric identifier. Data obtained from the iris can be converted into information through iris image processing, and in order to obtain accurate iris pixel results, an edge detection operator is required that can provide detailed and good image quality effects. In this research, a comparative analysis of the Canny, Sobel, Prewitt and Roberts edge detection operators was carried out on iris images. The purpose of performing a comparative analysis of edge detection methods is to compare the detection results of each edge detection operator on iris recognition detected by each operator. The results of the comparison of edge detection methods using precision tables can be analyzed to show that the Canny edge detection operator provides better, smoother and sharper edge results in actual edge point detection, namely 0.357867, while Sobel =, 0.210212, Prewitt = 0.212452 and Roberts = 0.279196. From these results it can be concluded that the edge detection results provided by Sobel and Prewitt are less sharp and sensitive to noise, and the comparison results can vary depending on the intensity of the image and the image object being compared.

At present, the edge detection method filters image edge points according to extreme image points, resulting in an unclear detected edge image and a low average energy value. An edge detection algorithm for machining part images based on mathematical morphology is proposed. The binary morphology of mathematical morphology is used to remove image noise. Using a two-dimensional wavelet transform, the edge information matrix in the horizontal and vertical directions of the image is calculated to determine the edge scale of the image. The mask operator in two directions of the image is calculated as a multiscale and multidirectional detection operator. According to the multiscale and multidirectional detection operator, the target edge detection process is designed to smooth the denoised machined part image, screen the image target edge points according to the maximum value points of the image edge gradient, segment the image target and background, and realize target edge detection. The images of machined parts collected in the normal machining room are divided into two categories according to the noise gradient, and the two groups of methods are compared. Experimental results: Compared with the method selected in this experiment, the average energy value of the detected target edge image is higher.

In the evaluation of tear film stability based on corneal topography, a pretreatment algorithm for tear film video was proposed for eye movement, eyelash reflection and background interference. First, Sobel operator was used to detect the blur image. Next, the target image with highlighted ring pattern was obtained by the morphological open operation performed on the grayscale image. Then the ring pattern frequency of the target image was extracted through the Hough circle detection and fast Fourier transform, and a band-pass filter was applied to the target image according to the ring pattern frequency. Finally, binarization and morphological closed operation were used for the localization of the ring pattern. Ten tear film videos were randomly selected from the database and processed frame by frame through the above algorithm. The experimental results showed that the proposed algorithm was effective in removing the invalid images in the video sequence and positioning the ring pattern, which laid a foundation for the subsequent evaluation of tear film stability.

Edge detection determines the boundaries of objects in an Image. Edge detection is a vital concept in object recognition and Image analysis. This paper evaluates the existing edge detection methods and proposes a new edge detection algorithm which uses the morphological operations, sobel operator, Gaussian Smoothing and masking. The novelty of the proposed algorithm is extracting continuous edges in the Image and removing spurious edges using m-connectivity. The paper introduces performance parameters for edge detection to determine which method gives good results. A parameter named Human Perception Clarity (HPC) is mathematically modeled and experimentally proves the efficacy of proposed algorithm.

A natural color mapping method has been previously proposed that matches the statistical properties (mean and standard deviation) of night-vision (NV) imagery to those of a daylight color image (manually selected as the "target" color distribution). Thus the rendered NV image appears to resemble the target image in terms of colors. However, in this prior method the colored NV image may appear unnatural if the target image's "global" color statistics are too different from that of the night vision scene (e.g., it would appear to have too much green if much more foliage was contained in the target image). Consequently, a new "local coloring" method is presented in the current paper, and functions to render the NV image segment-by-segment by using a histogram matching technique. Specifically, a false-color image (source image) is formed by assigning multi-band NV images to three RGB (red, green and blue) channels. A nonlinear diffusion filter is then applied to the false-colored image to reduce the number of colors. The final grayscale image segments are obtained by using clustering and merging techniques. The statistical matching procedure is merged with the histogram matching procedure to assure that the source image more closely resembles the target image with respect to color. Instead of using a single target color image, the mean, standard deviation and histogram distribution of a set of natural scene images are used as the target color properties for each color scheme. Corresponding to the source region segments, the target color schemes are grouped by their scene contents (or colors) such as green plants, roads, ground/earth. In our experiments, five pairs of night-vision images were initially analyzed, and the images that were colored (segment-by-segment) by the proposed "local coloring" method are shown to be much more natural, realistic, and colorful when compared with those produced by the "global-coloring" method.

This article proposes an implementation of Sobel edge detection on an FPGA (Field-Programmable Gate Array) platform.The suggested technique is built to quickly and precisely identify the borders or limits of an image.Image pre-processing, edge detection, and post-processing are just a few of the processing phases that make up the system architecture.Canny edge detection and Sobel edge detection techniques are combined to develop the edge detection algorithm.Non-maximum suppression and thresholding are used in the post-processing stage to improve the edge map's visual appeal.The results of the experiments show that the suggested system achieves excellent accuracy and real-time performance, making it appropriate for uses in robotics, surveillance, and autonomous vehicles.This study makes a positive impact on the advancement of hardware-based edge detection systems and offers a viable strategy for ongoing studies in this field.

Purpose: Misfiled cases in the PACS environment may create serious medical accidents in the hospitals and medical centers. The purpose of this study was to show a potential usefulness of an automated search method by use of biological fingerprints 2), i.e., some parts of chest radiographs, and image‐matching technique to find lost chest radiographs in a large database.Method and Materials: We employed five biological fingerprints in a chest radiograph such as cardiac shadow, lung apex, the superior mediastinum, the right lower lung, and a thoracic field. To find a lost image in a large database, biological fingerprints were extracted from a target image, i.e., the previous image of the same patient. Each of the biological fingerprints of the target image was used as a template for determination of the correlation value with the corresponding biological fingerprints in the current chest radiograph in the database. Our database used in this study included 36,228 patients with PA digital chest radiographs including 20,278 females and 15,950 males. Forty‐six target images were selected randomly, and used hypothetically as lost images to examine the potential usefulness of our method based on the biological fingerprints and image‐matching technique. Results: By use of all of images in our database, 78.3% (36/46) of the target images were correctly identified as the same patient's image by our method. Moreover, it was possible to identify 8.7% (4/46) of the additional target images correctly, when previous images with the top two to five correlation index were examined. These results appear to be promising in finding a patient with the lost images based on comparison with a large number of images.Conclusion: Our method by use of biological fingerprints and image‐matching technique has potential usefulness to find the lost chest radiographs automatically in the PACS server.

Histogram Matching (HM) is a well known technique for matching the colors of a source image to those of a reference image. A major application is High Dynamic Range Imaging, where images with different exposures have to be color matched. HM works best when the images are aligned and the color difference is small. However, due to camera or object motion, the images may not be aligned, which can result in color artifacts. Furthermore, HM typically involves brightening dark regions of the source image, which increases the image noise. As a result, there is a need for detecting and correcting color artifacts and increased image noise. In this paper we present a novel post-processing method for improving the quality of histogram matched images using statistical properties of the reference image. The proposed method is based on ensembles of neighboring pixels. We learn the statistics of such ensembles within the reference image (target image), which exhibits content difference in comparison to the source image. Based on these statistics, we detect and reconstruct faulty intensities, by following a naive Bayes approach. In addition to its relative easiness of implementation, experimental results show considerable subjective (visual) as well as objective (PSNR) improvements over the original HM. Moreover, promising results are obtained on comparisons of our method with Non-Local-Means denoising based post-processing, which is a state-of-the-art denoising method.

Edge detection is an important work for object recognition and is also an essential pre-processing step in image segmentation and visual analysis. This paper deeply studies the edge detection methods of the noisy images and concentrates on the mathematical morphology methods. By analyzing and studying the theory of mathematical morphology, the paper constructs edge detection operations and analyzes the specialties of the operator and the structure elements. Based on this, the paper proposes a new method of edge detection using mathematical morphology and image fusion. The operations can obtain clear and exact edge of the noisy images. By simulation and comparing with the traditional edge detection operations, the proposed method is more effective on noise restraining and retaining the image details.

Medical image three-dimensional (3D) interpolation is an important means to improve the image effect in 3D reconstruction. In image processing, the time-frequency domain transform is an efficient method. In this article, several time-frequency domain transform methods are applied and compared in 3D interpolation. And a Sobel edge detection and 3D matching interpolation method based on wavelet transform is proposed. We combine wavelet transform, traditional matching interpolation methods, and Sobel edge detection together in our algorithm. What is more, the characteristics of wavelet transform and Sobel operator are used. They deal with the sub-images of wavelet decomposition separately. Sobel edge detection 3D matching interpolation method is used in low-frequency sub-images under the circumstances of ensuring high frequency undistorted. Through wavelet reconstruction, it can get the target interpolation image. In this article, we make 3D interpolation of the real computed tomography (CT) images. Compared with other interpolation methods, our proposed method is verified to be effective and superior.

On the basis of Canny operator on image processing, The edge extraction of the fuzzy droplet images is carried out by combination of removing a small target and morphological open operation .First, Use edge detection operator to detect the image edge preliminary, and then call remove a small target which belongs to MATLAB internal function to filtering the results of the edge detection, and finally with morphological operations for final processing.The results showed that: the combination of Canny operator, open operation and remove a small target works much better than the classical Canny operator.

License Plate (LP) is the unique identification of a vehicle. License Plate Recognition (LPR) is considered as one of the promising aspects of applying computer seeing technology across intelligent transportation system. We used mathematical morphology and edge detection as a method for segmentation and extracting the vehicle license plate character, in Location of the vehicle plate. Initially, the color image was changed to a gray image, and by calculating the difference between the pixels and their neighbors in order to build the edge of the image. This makes the license panel appear clearly. The Sobel operator is applied to extract the edge of objects in the image. In order to obtain a smooth image, we apply the mathematical morphology of the images for dilation and erosion, and then we improve the efficiency of segmentation processing by using the images that are sent to the LP recognition stage. Multi-layer perceptron neural network will be used to recognize the license plate. Characters can be accurately extracted from the license plate due to the accurate extraction of the plate region.

Image steganography is a technique for obscuring secret message within image pixel matrix. It provides means for secretly communicating between two entities with the third party totally unaware of the embedded message. One of the most important methods for image steganography is edge detection technique, wherein secret data is inserted in LSBs of image edge pixels. Data embedding in edge pixels does not create notable distortion in image when compared to embedding data in non-edge pixels. Different types of edge pixel detectors are available including most renowned Canny edge detector, Sobel edge detector, Prewitt edge detector and many others. Hybrid edge detection uses a combination of different edge detectors for generating edge pixels of image. Message to be secretly communicated is inserted in the LSB of these edge pixels, and the image thus formed called stego image is sent to the concerned party. Major drawback of hybrid edge detection technique is its capacity. The number of edge pixels is very less in any image. In the last decade, many papers have focused on increasing capacity of edge detection by using different techniques. In this work, we have proposed an extremely high-capacity hybrid edge detection technique by using data compression. Also, data is encrypted and then inserted in the cover image pixels. For message integrity, SHA512 hash function is used. Subsequently, this work not only improves capacity of edge detection while maintaining the image quality but also provides security and message integrity.