We address the problem of food items detection and recognizing different food categories in images. Given the variety of food items with low inter- and high intraclass variations and the limited information contained in a single image, the problem is known to be particularly hard. In order to achieve better detection and recognition capabilities, we propose a joint use of multiple classifiers trained on features extracted via multiple deep models using different fusion techniques, including an early and two different late fusion schemes, namely induced order weighted averaging and particle swarm optimization based fusion. Moreover, we assess the performance of different deep models in food items detection and recognition. Experimental evaluations are carried out on two large-scale benchmark datasets, demonstrating better results for the proposed approach.
This paper introduces a new application of computer vision. To the best of the author’s knowledge, it is the first attempt to incorporate computer vision techniques into room interior designing. The computer vision based interior designing is achieved in two steps: object identification and color assignment. The image segmentation approach is used for the identification of the objects in the room and different color schemes are used for color assignment to these objects. The proposed approach is applied to simple as well as complex images from online sources. The proposed approach not only accelerated the process of interior designing but also made it very efficient by giving multiple alternatives.
Background cluttering badly affects the performance of Skin detection. In highly cluttered images, skin detection becomes more difficult and the algorithm can’t differentiate between the skin and non-skin pixels. In this paper, we introduce saliency algorithm for removing the irrelevant information especially the skin like regions, in the background of the human images to tackle the background cluttering problem and improve the performance of skin detection algorithms in images with complex backgrounds. Extensive experimentation on highly cluttered and complex images shows that saliency algorithm further enhances the performance of skin detection algorithms not only in terms of false positive rate but in true positive rate, true negative, false negative rate, accuracy and precision too.
This presentation introduces a novel model for analyzing the optical interface performance degradation due to scratches on optical fiber endface. The model indicates that the contribution to the return loss of a scratch is determined by its size, location and its relative reflectivity, which is defined as the ratio of the average reflectivity of the scratch to the base reflectivity of the defectless endface. Based on this new model, the effects on return loss are analyzed for scratches of various numbers, different sizes, with different relative reflectivities, and at different locations. This quantified analysis provides a solid base to establish the specifications of inspection criteria of optical interface. With the new model, the relative reflectivity of a scratch was tested, and estimations of the return loss of scratched connectors were performed, which were in good agreement with measurement results.