Search

International audience; We extend the notion of content based image retrieval to patch retrieval where the goal is to find the similar patches to a query patch in a large image. Naive searching for similar patches by sequentially computing and comparing descriptors of sliding windows takes a lot of time in a large image. We propose a novel method to compute descriptors for all sliding windows independent from number of patches. We rely on tree representation of the image and exploit the histogram nature of pattern spectra to compute all the required descriptors in parallel. Computation time of the proposed method depends only on the number of tree nodes and is free from query selection. Experimental results show the effectiveness of the proposed method to reduce the computation time and its potential for object detection in large images.

Retargeting algorithms are used to transfer and display images on devices with various sizes and resolutions. All of these algorithms try to preserve the important parts of image against distortions while producing a retargeted image with visual quality comparable with the original one. The main challenge in different algorithms is to find a suitable energy function that properly estimates the importance of each pixel in image. Hence the energy map needs to be improved. In this paper we propose a novel energy function which combines the information from saliency map, depth map and gradient map. We also present an algorithm to adaptively assign proper weights to these three importance maps for each input image. Then we calculate a switching threshold based on energy map that determines when to apply seam carving or scaling. The idea is to use a combination of seam carving and scaling to preserve the structure of important parts of image against distortion when the image size decreases beyond a point. This method reduces shape deformations and visual artifacts in salient regions of images and produces better quality output images. The results of the proposed method show superior visual quality in produced images in comparison to the state-of-the-arts.

The topic of Person Re-Identification (Re-ID) is currently attracting much interest from researchers due to the various possible applications such as behavior recognition, person tracking and safety purposes at public places. General approach is to extract discriminative color and texture features from images and calculate their distances as a measure of similarity. Most of the work consider whole body to extract descriptors. However, human body maybe occluded or seen from different views that prevent correct matching between persons.

Automatic liver segmentation plays a vital role in computer-aided diagnosis or treatment. Manual segmentation of organs is a tedious and challenging task and is prone to human errors. In this paper, we propose innovative pre-processing and adaptive 3D region growing methods with subject-specific conditions. To obtain strong edges and high contrast, we propose effective contrast enhancement algorithm then we use the atlas intensity distribution of most probable voxels in probability maps along with location before designing conditions for our 3D region growing method. We also incorporate the organ boundary to restrict the region growing. We compare our method with the label fusion of 13 organs on state-of-the-art Deeds registration method and achieved Dice score of 92.56%.

This paper presents a novel two-pronged framework for person re-identification. Its idea articulates over the fact that distinct descriptors manifest different ranking scores for the same probe pattern. Thus, if conveniently fused, the descriptors in hand are ought to compensate each other, leading to significant improvements. In this respect, this paper proposes a learning-free weighting method that penalizes and averages the re-identification estimates (e.g., distances) pointed out by different descriptors according to their confidence in evidencing the correct match, to a given probe person, among a given gallery. We particularly show that tangible improvements can be attained with respect to utilizing each descriptor individually. Moreover, we consider a confidence measure mechanism that treats the mutual pairwise distances within the gallery, in order to raise the scores obtained at the fusion stage, and we show that interesting improvements can be achieved. We evaluate the proposed framework on four benchmark datasets and advance late works by large margins.

This paper presents a novel person re-identification framework based on data fusion. The pipeline of the proposed method is composed of two stages. First, a metric learning paradigm is applied on a bunch of distinct feature extractors to produce an ensemble of estimated distance measures, which are subsequently penalized according to their confidence in evidencing the correct matches from the false ones, and averaged as to draw a final decision. Second, the close persons from the gallery are selected based on the previously fused distance estimates, and utilized to build a dictionary as to reconstruct a given probe pattern. Evaluated on benchmark datasets, the proposed framework advances the state-of-the-art by interesting margins. In particular, Rank1 gains amounting to about 12%, 1%, 6%, and 12%, were scored on VIPeR, CAVIAR4REID, iLIDS, and 3DPeS, respectively.

Human re-identification is still a challenging task due to the human pose and illumination variations. Nowadays, surveillance cameras with high frame rate are capable of capturing several consecutive frames from each person. Multi-shot images provide richer information of the target person compared to a single-shot image. They, however, produce a high cost of information redundancy which may degrade the performance of re-identification systems. In this paper, we propose a novel framework that combines sparse coding and manifold constraints to extract discriminative information from multi-shot images of one pedestrian for person re-identification across a set of non-overlapped surveillance cameras. The evaluation over two standard multi-shot datasets shows very competitive accuracy of our framework against the state-of-the-art.

Segmentation of X-ray bone images is of concern in many medical applications such as detection of osteoporosis and bone fractures. Segmentation of such images is a challenging process. Varying brightness throughout the image makes it difficult to separate bones from background and soft tissue. Costume made as well as standard segmentation methods, such as active contour and region growing, have been applied to bone X-ray images. Although each method could perform well for some images, due to variety of bone structures and lighting conditions none of these methods can be considered as complete. In this paper we present a new bone segmentation method in which an image goes through preprocessing steps such as noise cancellation and edge detection. Analysis of intensity fluctuations in all rows of the image results in more accurate segmentation of bone regions. Visual evaluation show that the proposed algorithm segments bones better than conventional and some recent bone segmentation approaches.

Re-identification systems aim at recognizing the same individuals in multiple cameras and one of the most relevant problems is that the appearance of same individual varies across cameras due to illumination and viewpoint changes. This paper proposes the use of Minimum Multiple Cumulative Brightness Transfer Functions to model this appearance variations. It is multiple frame-based learning approach which leverages consecutive detections of each individual to transfer the appearance, rather than learning brightness transfer function from pairs of images. We tested our approach on standard multi-camera surveillance datasets showing consistent and significant improvements over existing methods on two different datasets without any other additional cost. Our approach is general and can be applied to any appearance-based method.

Retargeting algorithms are needed to transfer an image from a device to another with different size and resolution. The goal is to preserve the best visual quality for important objects of the original image. In order to reduce image size, pixels should be removed from less important parts of the image. Therefore, we need an energy function to select less important pixels in seam carving. Various energy functions have been proposed in previous works to minimize the distortion in salient objects. In this paper we combine three different importance maps to form a new energy map. We first use both gradient and depth maps to highlight the values in the saliency map, eventually generates the final energy map. Experimental results using the proposed energy map show better visual appearance in comparison to previous algorithms even at high resizing percentage. The visual artifacts that cause shape deformation in salient objects and deteriorates geometrical consistency of the scene are considerably reduced in our proposed algorithm.

Multifocus image fusion plays an important role in image processing and machine vision applications. In frequent occasions, captured images are not focus throughout the image because the optical lenses that are commonly used for producing image have limited depth of field. Therefore only the objects that are near the focal range of the camera are clear while other parts are blurred. One solution is to capture several images with different focal ranges and combine them to produce an image that is focused everywhere. To identify focused regions, current implementations of the mentioned solution use spatial or transform-domain. These methods usually suffer from artifacts such as blockiness or ringing. In this paper we have defined an energy term and categorized a region's energy into low, medium, and high levels. Then based on the level of energy each pixel is defined as either focused or not. The output fused image is constructed from focused pixels of the two source images. Experimental results reveal the superiority of our method compared to comparable algorithms.

With due attention to industry deployment and extension of urban zones, early warning systems have critical role in giving emergency response to unexpected events. Video-base fire detection is a low cost and effective method for this purpose. Most of available fire detection methods only use color information in detection process that is inaccurate. This paper intends to increase the accuracy of fire detection in video sequences using motion detection and combination of two classifiers. Movement of pixels and their color in the YCbCr space are considered for detection. Using this combined method, false alarms due to movements of ordinary objects with fire-like color, are greatly reduced in comparison with other color based fire detection systems.

Population of old generation is growing in most countries. Many of these seniors are living alone at home. Falling is among the most dangerous events that often happen and may need immediate medical care. Automatic fall detection systems could help old people and patients to live independently. Vision-based systems have advantage over wearable devices. These visual systems extract some features from video sequences and classify fall and normal activities. These features usually depend on camera's view direction. Using several cameras to solve this problem increases the complexity of the final system. In this paper, we propose to use variations in silhouette area that are obtained from only one camera. We use a simple background separation method to find the silhouette. We show that the proposed feature is view invariant. Extracted feature is fed into a support vector machine for classification. Simulation of the proposed method using a publicly available dataset shows promising results.

Population of old generation that live alone is growing in most countries. Surveillance systems help them stay home and reduce the burden on the healthcare system. Automatic visual surveillance systems have advantages over wearable devices. They extract features from video sequences and use them for event classification. But these features are dependent on the position of cameras relative to the person. Therefore they need multi-camera for more accuracy that increases cost and complexity. In this paper we propose using silhouette area combined with inclination angle as robust features that can be measured using only one camera with an arbitrary direction. Through rigorous simulations on a publicly available dataset the error rate of the system is found to be less than 1%.