Image Database

This paper presents the results of handwritten digit recognition on well-known image databases using state-of-the-art feature extraction and classification techniques. The tested databases are CENPARMI, CEDAR, and MNIST. On the test data set of each database, 80 recognition accuracies are given by combining eight classifiers with ten feature vectors. The features include chaincode feature, gradient feature, profile structure feature, and peripheral direction contributivity. The gradient feature is extracted from either binary image or gray-scale image. The classifiers include the k-nearest neighbor classifier, three neural classifiers, a learning vector quantization classifier, a discriminative learning quadratic discriminant function (DLQDF) classifier, and two support vector classifiers (SVCs). All the classifiers and feature vectors give high recognition accuracies. Relatively, the chaincode feature and the gradient feature show advantage over other features, and the profile structure feature shows efficiency as a complementary feature. The SVC with RBF kernel (SVC-rbf) gives the highest accuracy in most cases but is extremely expensive in storage and computation. Among the non-SV classifiers, the polynomial classifier and DLQDF give the highest accuracies. The results of non-SV classifiers are competitive to the best ones previously reported on the same databases.

... 7 Conclusions In this paper, we have proposed a geometry-based image representation scheme and an algo-rithm/function for retrieving i&D images of relevance (based on spatial similarity) to ... The algorithm is robust-in the sense that it can recognize translation and scale ...

Abstract: Advances in data storage and image acquisition technologies have enabled the creation of large image datasets. In this scenario, it is necessary to develop appropriate information systems to efficiently manage these collections. The commonest approaches use the so-called Content-Based Image Retrieval (CBIR) systems. Basically, these systems try to retrieve images similar to a user-defined specification or pattern (eg, shape sketch, image example). Their goal is to support image retrieval based on content properties (eg, ...

Content-based image retrieval consists in retrieving from an image database the most similar image with respect to a query, according to some similarity measure. This scenario has numerous specic applications that include bioinformatics and medical imaging, among others. However, because the size of image repositories grows very fast, nding patterns in images requires an index to avoid a sequential scan,

With the onslaught of multimedia in the near past, there has been a tremendous increase in the uses of images. A very good example of which is the web on which most of the documents contain images. Other than this the images are being used in other applications like weather forecasting, medical diagnosis, police department. In R-Tree implementation of image database, images are made available to the program which are then stores in the database. The image database is presented using R-tree and the database is stored in separate file .This R-tree implementation results in both update as well as efficient retrieval of images from hard disk [1][2][4]. We use the similarity based retrieval feature to retrieve the required number of similar images being inquired by the user [3][5][6]. Distance matrix approach is used to find similarity of images [7]. Sobel edge detection algorithm is used to form sketches. If sketch of image is entered for similarity based retrieval, then sketches of stored images are formed and these sketches are compared with input image (sketch) using distance matrix approach[8][9].

With the onslaught of multimedia in the near past, there has been a tremendous increase in the uses of images. A very good example of which is the web on which most of the documents contain images. Other than this the images are being used in other applications like weather forecasting, medical diagnosis, police department. In R-Tree implementation of image database, images are made available to the program which are then stores in the database. The image database is presented using R-tree and the database is stored in separate file .This R-tree implementation results in both update as well as efficient retrieval of images from hard disk [1][2][4]. We use the similarity based retrieval feature to retrieve the required number of similar images being inquired by the user [3][5][6]. Distance matrix approach is used to find similarity of images [7]. Sobel edge detection algorithm is used to form sketches. If sketch of image is entered for similarity based retrieval, then sketches of stored images are formed and these sketches are compared with input image (sketch) using distance matrix approach[8][9].

Diabetic retinopathy (DR) has been identified as a leading cause of blindness. One type of lesion, neovascularization (NV), indicates that the disease has entered a vision-threatening phase. Early detection of NV is thus clinically significant. Efforts have been devoted to use computer-aided analyses of digital retina images to detect DR. However, developing reliable NV detection algorithms requires large numbers of digital retinal images to test and refine approaches. Computer simulation of NV offers the potential of developing lesion detection algorithms without the need for large image databases of real pathology. In this paper, we propose a systematic approach to simulating NV. Specifically, we propose two algorithms based on fractal models to simulate the main structure of NV and an adaptive color generation method to assign photorealistic pixel values to the structure. Moreover, we develop an interactive system that provides instant visual feedback to support NV simulation guided by an ophthalmologist. This enables us to combine the low level algorithms with high-level human feedback to simulate realistic lesions. Experiments suggest that our method is able to produce simulated NVs that are indistinguishable from real lesions.

Mei-Ling Shyu Department of Electrical and Computer Engineering University of Miami Coral Gables, FL 33124, USA 1-305-284-5566 shyu@miami.edu ... Shu-Ching Chen, Min Chen Distributed Multimedia Information System Laboratory School of Computer Science Florida ...

Color has been widely used for content-based image and video retrieval. However its robustness, effectiveness, and efficiency in image indexing are still open issues. The definition of feature similarity also plays a fundamental role in content-based retrieval, as images with "similar" feature distributions are considered similar in appearance without requiring any semantic expression of this. This paper reviews the methods

Grid services offer a number of advantages in the field of medical imaging. Many image processing algorithms are computationally intensive and require high specification hardware or take a long time to run. The prospect of being able to use dedicated clusters of high end workstations on a remote network, or indeed several networks, with only a few clicks of the