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.
Recently, a lot of works have shown the advantages of utilizing the deep descriptors, obtained from the features of the last convolution layer in CNNs, on image retrieval. In this paper, we focus on augmenting and fusing CNN features for the image retrieval task. We first investigate the effects of network rotation, and then propose two models for deep feature augmenting: single model augmenting and...
Person re-identification is best known as the problem of associating a single person that is observed from one or more disjoint cameras. The existing literature has mainly addressed such an issue, neglecting the fact that people usually move in groups, like in crowded scenarios. We believe that the additional information carried by neighboring individuals provides a relevant visual context that can...
Digital images have become very important in our daily lives and some other important areas such as medicine, journalism and it can be also used as forensic evidence. However, the simplicity of using digital images with freely available software tools makes the authenticity of images questionable. The most common image forgery type is copy move forgery because it can be done easily but the detection...
Omnidirectional imaging, also known as 360° and spherical imaging, records all 360° of a scene from a specific spatial position, thus offering the user the capability to enjoy three rotational degrees of freedom (3-DoF). To offer a good quality of experience, omnidirectional imaging requires very high bitrates as high spatial resolution are a must and, ideally, also high frame rates. Due to the lack...
In this paper, we proposed a fast coding unit (CU) size decision algorithm for High Efficiency Video Coding (HEVC) medical image lossless coding. In detailed, we used the coding information obtained after checking the first two prediction unit (PU) modes inter 2N×2N and Skip to determine whether or not to continue partitioning the current CU. Eight features are extracted from the coding information...
Human action recognition is a challenging and active research area in computer vision. In this paper, we propose a simple yet effective method, called the locality-constrained linear coding (LLC) based two-dimensional spatial-temporal templates, to learn a discriminative representation for human action recognition. Our proposed method calculates twodimensional spatial-temporal templates from each...
A novel selective image authentication system based on the robust digital watermarking is proposed. The discrete shearlet transform is performed in order to extract the feature vector from the image. The cone-adapted version of the transform is used to calculate the shearlet coefficients more precisely and to avoid the biased treatment. The proposed approach allows to use conventional cryptographic...
A speeding up robust identification scheme for JPEG images is proposed in this paper. The aim of the identification is to robustly identify JPEG images that are generated from the same original image, under various compression conditions such as differences in compression ratios and initial quantization matrices. The conventional scheme that we focus on uses visually protected features to achieve...
As the usage areas of the images increase, the functions of various image editing software are increasing. Easy-to-use software has caused the images to be tampered with easily. Many Copy-Move Forgery Detection (CMFD) algorithms have been developed against these attacks. In literature CMFD methods are divided into block based and keypoint based methods. In this paper, recent works in keypoint based...
This paper presents a comparative study of two recent word spotting techniques ([1] and [2]) directly in the run-length compressed domain. The first technique is based on partial decompression and limited usage of OCR, and the second technique is completely decompression-less and OCR-less. Both the word spotting techniques use word bounding box ratio feature initially for matching words in the database...
While much progress has been achieved in the field of content-based image retrieval (CBIR), almost all CBIR techniques operate on pixel data although virtually all images are stored in compressed form. In this invited paper, we present efficient and effective CBIR techniques that operate directly in the compressed domain and thus do not require full decompression for feature extraction. In particular,...
In this paper, we propose a palmprint recognition scheme using histograms of sparse codes (HSC) as a new feature for palmprint image. In the feature extraction stage, the HSC feature is obtained by computing sparse codes for a given dictionary from a palmprint image, which results in a feature image. In the feature encoding stage, a hash table is designed from the feature image using the binary hashing...
In this paper we present an adversary-aware double JPEG detector which is capable of detecting the presence of two JPEG compression steps even in the presence of heterogeneous processing and counter-forensic (C-F) attacks. The detector is based on an SVM classifier fed with a large number of features and trained to recognise the traces left by double JPEG detection in the presence of attacks. Since...
Developing a robust vehicle tracking system is an active area of study in the field of automotive tracking. Such a system is also helpful in providing support to collision avoidance, lane change instructions and merge assistance. Fast Compressive Tracking (FCT) algorithm has recently been proposed for object tracking. FCT has not been explored on vehicle tracking datasets LISA and TME Motorway. In...
With the widespread use of digital images almost every field so authentication of them has become increasingly important. So researchers proposed various methods to cope with this issue recently. We proposed a new fast and effective method to cope with the digital image copy move forgery. In this method the keypoints and their descriptors are extracted from the input image by using Scale Invariant...
As an important research topic in computer vision, abnormal detection has gained more and more attention. In order to detect abnormal events effectively, we propose a novel method using optical flow and deep autoencoder. In our model, optical flow of the original video sequence is calculated and visualized as optical flow image, which is then fed into a deep autoencoder. Then the deep autoencoder...
Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An emerging question, however, is whether these model compression techniques hurt DNNs learning ability other than classifying images on a single dataset. Our preliminary...
This paper proposes a feature fusion based method for JPEG double compression detection. When extracting the fusion features, the Markov model of the first digits of DCT coefficients and the difference of adjacent coefficients extracted from JPEG images are fused to a big feature vector, and then the Sammon mapping method is applied for dimensionality reduction. Finally, the Support Vector Machine...
Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the...
Traffic scene recognition is an important and challenging issue in Intelligent Transportation Systems (ITS). Recently, Convolutional Neural Network (CNN) models have achieved great success in many applications, including scene classification. The remarkable representational learning capability of CNN remains to be further explored for solving real-world problems. Vector of Locally Aggregated Descriptors...
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.