The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first deeplearning neural network for reflection and rotation symmetry detection (Sym-NET),...
A vast majority of consumer cameras operate the rolling shutter mechanism, which often produces distorted images due to inter-row delay while capturing an image. Recent methods for monocular rolling shutter compensation utilize blur kernel, straightness of line segments, as well as angle and length preservation. However, they do not incorporate scene geometry explicitly for rolling shutter correction,...
This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and optical flow is propagated bidirectionally in a unified framework. The segmentation branch is based on a fully convolutional network, which has been proved effective...
Image segmentation has always been an important research direction in the field of images processing, however, due to the long cycle of algorithm, the image segmentation techniques have never been widely applied. According to the problem above, a image segmentation algorithm of Gaussian Mixture Model (GMM) based on Map/Reduce is proposed to improve the real-time performance. Firstly, the architecture...
We present a novel and effective approach for generating new clothing on a wearer through generative adversarial learning. Given an input image of a person and a sentence describing a different outfit, our model “redresses” the person as desired, while at the same time keeping the wearer and her/his pose unchanged. Generating new outfits with precise regions conforming to a language description while...
In this paper, we propose Sequential Grouping Networks (SGN) to tackle the problem of object instance segmentation. SGNs employ a sequence of neural networks, each solving a sub-grouping problem of increasing semantic complexity in order to gradually compose objects out of pixels. In particular, the first network aims to group pixels along each image row and column by predicting horizontal and vertical...
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance...
Stereo matching is important in the area of computer vision and photogrammetry. We present a stereo matching algorithm to refine depth map by using stereo image pair. The reference image is segmented by using hill-climbing algorithm and Scale Invariant Feature Transform (SIFT) feature descriptor with Sum of Absolute Difference (SAD) local stereo matching is performed. Next, we extract a set of disparity...
The hand segmentation is the critical pre-processing of the gesture recognition application. Nowadays, to achieve a robust hand segmentation under cluttered background is still challenging. Advanced research in model-driven approach based on the depth information has obtained impressive performance. However, it is unable to deal with the hand very close to the body part. Also, a large number of marked...
Although image segmentation technology has achieved rapid development, threshold method is still an indispensable part in many practical applications. The most advanced methods do not perform well in the segmentation of many different types of images. Therefore, it is expected that the optimal segmentation method can be obtained for images with different modalities. In this paper, a robust threshold...
Owing to the elevated intra/inter variation among the foreground and background text of various document images, the text segmentation from the poorly degraded document images is the difficult job. This paper presents the document image binarization method by adaptive image contrast which is the integration of the local image gradient and the local image contrast which is lenient to background and...
Osteoarthritis has become a very rapidly spreading disorder of bones and joints among old people and young athletes indulging in sports such as soccer, hockey, etc. Injuries of the knee like tears in the meniscus can be seen very commonly in young athletes as well as the aged people. The Computer-Aided Diagnosis (CAD) systems help to a large extent and can play a major role in their detection. In...
The most critical technique in the train number detection process is the extraction and division of vehicle image. This paper introduces an intelligent detection system based on two cameras. First of all, on the basis of kalman prediction tracking algorithm, this paper puts forward a kind of collaborative tracking discriminant train number system, and determining the best Angle of the camera. To correct...
Recent advances in camera technologies has led to the design of plenoptic cameras. This camera type can capture multiple images of the same scene using arrays of microlenses, where each microlens has a shifted location providing a separate view of the scene. Such a design results in a superior performance as compared to traditional cameras, enabling multi-view or multi-focal imaging captured in a...
An accurate segment-based cost aggregation method is proposed in this paper. Segment-based methods can speed up the procedure according to the assumption that pixels belonging the same segment should share the same physical property. One of the most critical problems of those methods is the limited pixels within the corresponding segment. To enlarge supporting region of aggregation efficiently, we...
Brain tumour diagnosis is usually a vital use of medical image processing, where clustering technique commonly used with medical application especially regarding brain tumour diagnosis with magnetic resonance imaging (MRI). In this MRI has been considered because it provides accurate visualization of anatomical structure of tissues. The conventional mean shift technique utilizes radially symmetric...
Region growing is an image segmentation algorithm extremely useful for continuous regions extraction. It defines an initial set of seeds, according to a specific criteria, and iteratively aggregates similar neighbor pixels. The algorithm converges when no pixel aggregation is performed in a certain iteration. Within this research project, region growing is employed for the segmentation of cracks in...
An alternative is presented to create an image mosaic commuting between the features extraction SIFT (Scale Invariant Features) and SURF (Speeded-Up Robust Features) algorithms. Due to the ambiguity in detail classification and switching between these algorithms, it is proposed to use a pre-processing stage and a fuzzy logic system for the feature extraction. Image register presents the intensity...
In this paper, a robust level set method is proposed for image segmentation. Traditional level set methods are sensitive to noise in images which greatly limits its application in real project. To overcome this shortcoming, the fractional order regularization and Markov random fields term are incorporated into the traditional level methods in this paper. The fractional order regularization can reveal...
Medical image segmentation is an important application in medical image processing. In order to improve the efficiency of Medical image segmentation, a method to select optimal threshold by PSO algorithm with Dynamic Inertia Weight(DW-PSO) is proposed. It makes the proportion of the local and global searching ability can be effectively controlled in the whole process of optimal searching. Compared...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.