Using hand gestures is one of the most natural ways of interacting with the computer and most importantly correct interpretation of moving hand gestures in real-time has many applications. In this paper, the author ha...
详细信息
ISBN:
(纸本)9781538642733
Using hand gestures is one of the most natural ways of interacting with the computer and most importantly correct interpretation of moving hand gestures in real-time has many applications. In this paper, the author has designed and developed a system which can recognize gestures in front of a web camera real time using motion history images (NMI) and feedforward neural networks. Firstly, background from captured frames is removed using Gaussian mixture based background/foreground segmentation algorithm in order to capture moving areas in the frame and thereafter median filtering has applied to remove random noise from the frame. Then binary thresholding with Otsu's binarization has applied and it will identify optimal threshold value and these processed frames are merged and cumulative motion history image is generated using a developed algorithm based on the structural similarity measure. Structural similarity between the cumulated image and the initial frame also calculated and used in this algorithm. Finally feed forward neural network with stochastic gradient-based optimizer has used to classify the gestures.
The existing image block compression method does not reduce the amount of data after the image block processing. For the image with large amount of raw data, such as high-resolution remote sensing images, the image co...
详细信息
The existing image block compression method does not reduce the amount of data after the image block processing. For the image with large amount of raw data, such as high-resolution remote sensing images, the image compression will consume more hardware resources and cause great pressure on the compression performance. Aiming at this situation, a method for block compressed of images based on data-hiding is proposed. The reference image block and similar image blocks are judged by the similarity of image blocks. The number of similar image blocks is hidden in the reference image block by data-hiding, and only the reference image blocks are subjected to JPEG2000 compression. The experimental results show that the method reduces the amount of data before image compression by 1/3 and increase the compression ratio of image compression by 1.5 times.
Transmission line deep learning image recognition is one of the most important breakthroughs in the field of artificial intelligence in recent ten years. It has achieved great success in many fields, such as sample re...
详细信息
Fabric inspection is an important part of testing the quality of textiles. Influenced by labor and cloth inspection machines, traditional fabric inspection results in low detection efficiency and high error inspection...
详细信息
ISBN:
(纸本)9781538649916
Fabric inspection is an important part of testing the quality of textiles. Influenced by labor and cloth inspection machines, traditional fabric inspection results in low detection efficiency and high error inspection. In this paper, we propose a fast and efficient defect detection scheme by installing a camera to grab a cloth image in a weaving circle machine. In the progress of fabric weaving, there are three types of flaws: spots, holes and lines on the fabric. In our scheme, The Blob feature point detection algorithm is used to detect the spots, the Canny operator contour detection method is used to detect the holes, and the proposed rotation screenshot gray integral projection method is used to detect the lines. The experiment results show that our fabric inspection scheme presents higher detection efficiency than existing ones.
The rapid development of Artificial Intelligence has revolutionized the area of autonomous vehicles by incorporating complex models and algorithms. Self-driving cars are always one of the biggest inventions in compute...
详细信息
image editing software is often characterized by a seemingly endless array of toolbars, filters, transformations and layers. But recently, a counter trend has emerged in the field of image editing which aims to reduce...
详细信息
In order to improve the efficiency of crack detection of concrete bridge structures, a new method based on computervision technology and coordinate mapping is proposed. In this research, this crack measurement system...
详细信息
ISBN:
(纸本)9781538649916
In order to improve the efficiency of crack detection of concrete bridge structures, a new method based on computervision technology and coordinate mapping is proposed. In this research, this crack measurement system is integrated mainly with a high magnification image acquisition system, a two-dimensional electric cradle head device and a laser ranging system. It has a set of observing coordinate system. Firstly, the marking points' image coordinates are mapped to the observation coordinates. Secondly, according to the marking points' observation coordinates, the measured crack's coordinates are mapped to a same world coordinates so as to realize the spatial location of the measured cracks regardless of different test cycles or instrument's setup positions, which is a great convenience for the review detection of surface cracks of concrete bridge structures. The experiments show that this method is efficient and convenient. It can automatically locate the measured cracks within 16 s, and the deviation is not more than +/- 0.07 degrees. At a distance of 100 m, the measurement accuracy of crack width is better than +/- 0.12 mm.
Deep neural networks have demonstrated their effectiveness in computervision, especially for image classification and detection. Mixup is recently proposed as a data augmentation scheme, which applies linear combinat...
详细信息
ISBN:
(纸本)9781450376822
Deep neural networks have demonstrated their effectiveness in computervision, especially for image classification and detection. Mixup is recently proposed as a data augmentation scheme, which applies linear combination of two random training examples and corresponding targets. However, the linear assumption is inappropriate for training a non-linear model. In this paper, we propose a self-supervised method which requires the consistency of original and mixed images on feature space. Our work is motived by the semantic information is related to the relative position of features. To implement this idea effectively and efficiently, we perform two-stage of training procedure, i.e., running estimation of class centers of original data in feature space, and training deep neural networks with modified loss term of Mixup. Besides, the proposed approach is also compatible with other variants of Mixup. We validate our approach on two popular image classification datasets, CIFAR10 and CIFAR100 by a variety of advanced deep neural networks, and demonstrate consistent generalization improvements, sometimes significantly. We also conduct analytical experiments to evaluate the robustness of our method to hyperparameters.
Inferring the depth and shape of remote objects and the camera motion from a sequence of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. This...
详细信息
ISBN:
(纸本)0818620579
Inferring the depth and shape of remote objects and the camera motion from a sequence of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. This problem is overcome by inferring shape and motion without computing depth as an intermediate step. On a single epipolar plane, an image sequence can be represented by the F × P matrix of the image coordinates of P points tracked through F frames. It is shown that under orthographic projection this matrix is of rank three. Using this result, the authors develop a shape-and-motion algorithm based on singular value decomposition. The algorithm gives accurate results, without relying on any smoothness assumption for either shape or motion.
Diseases of dermatological nature have become quite common given the deteriorating environmental conditions, making visits to a dermatologist more frequent. However, a visit to a dermatologist may not always be very f...
详细信息
暂无评论