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.
Deep convolution networks based strategies have shown a remarkable performance in different recognition tasks. Unfortunately, in a variety of realistic scenarios, accurate and robust recognition is hard especially for the videos. Different challenges such as cluttered backgrounds or viewpoint change etc. may generate the problem like large intrinsic and extrinsic class variations. In addition, the...
The article shows the methods of vehicle recognition on the image sequence and its trajectory registration. As a recognition algorithm authors used Viola-Jones method with optical flow filter and the deep convolutional neural network in combination with sliding window technique for vehicle detection task. Also authors analyze approaches to registration of detected vehicle trajectories on image sequence...
The artificial visual detection and recognition of bridges' cracks bear great dangers, therefore, we put forward a method of digital and intelligent detection of bridges fractures, combined with machine vision and the Deep Belief Network technologies. This method adopts Raspberry Pi to collect and pre-process images, to transmit images data by the GPRS / 3G or wired networks. And it uses high-level...
The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds. Existing works have confirmed that, in order to capture the subtle differences across the categories, automatic localization of objects and parts is critical. Most approaches for object and part localization rehed on the bottom-up pipeline, where thousands of region proposals are generated...
The availability of mobile access has shifted social media use. With that phenomenon, what users shared on social media and where they visited is naturally an excellent resource to learn their visiting behavior. Knowing visit behaviors would help market survey and customer relationship management, e.g., sending customers coupons of the businesses that they visit frequently. Most prior studies leverage...
We propose a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high dimensional space to avoid the computationally expensive training step. We estimate regression models for each test image using the class specific gallery subspaces. Images of the test set are then reconstructed using the regression models. Based...
Heterogeneous face recognition (HFR) has a prominent importance in sophisticated face recognition systems. Thermal to visible scenario, where the gallery and the probe images are respectively captured in visible and long wavelength infrared (LWIR) band, is one of the most challenging and interesting HFR scenarios. Since the formation of thermal images does not require an external illumination source,...
Eye state recognition is still a challenging work in the field of computer vision. Many researchers have described their methods which can work well with frontal face views, but not with variations of head poses. Some have explained that their methods deal effectively with head pose problems, yet the whole system is complex to implement and consumes a lot of processing time. In this paper, a novel...
In this paper, we propose a low-complexity graphic constellation projection (GCP) algorithm for automatic modulation classification (AMC), where the recovered symbols are projected into artificial graphic constellations. Unlike the existing feature- based (FB) algorithms, we convert the AMC problem into an image recognition problem. Subsequently, the deep belief network (DBN) is adopted to learn the...
In recent years, artificial intelligence technology has developed rapidly, and deep learning has been widely used in many areas. The performance of deep learning is particularly prominent in image recognition. This paper proposes a method to achieve efficient image recognition based on deep neural network using a small amount of data, which can be applied to home access control systems. The recognized...
This paper presents an approach to detect and recognize actions of interest in real-time from a continuous stream of data that are captured simultaneously from a Kinect depth camera and a wearable inertial sensor. Actions of interest are considered to appear continuously and in a random order among actions of non-interest. Skeleton depth images are first used to separate actions of interest from actions...
Herbal medicines can be used in treating health conditions under qualified medical observation. Various advantages are perceived by many consumers as being associated with using herbal medicines compared to conventional pharmaceutical products, such as the reduced risk of side effects, effectiveness with chronic conditions, lower cost and large availability, although robust evidence supporting such...
Pollen granules are one of the most stable microstructures of herbal flowers, and their ektexines possess strong anti-acid, anti-base and anti-biolysis properties. Therefore, the microstructures of pollen granules are not destroyed during storage, manufacturing and the production of different preparations. The shapes, sizes and colors of pollen granules are different in different families, genera...
The proposed system for automobile security is a face detection and recognition application that control the automobile to be operated or restricted. This system is established for all types of door locks and particularly for automobiles. By using this methodology, resulted a better quality product with respect to documentation standards, code optimization, user acceptance due to adequately efficient,...
Image recognition using Deep Learning has been evolved for decades though advances in the field through different settings is still a challenge. In this paper, we present our findings in searching for better image classifiers in offline and online environments. We resort to Convolutional Neural Network and its variations of fully connected Multi-layer Perceptron. Though still preliminary, these results...
As the issue of robustness of face recognition based on depth image sets, we propose that multiple Kinect images is being as a set of images, and depth data captured is used to automatically estimate poses and crop face area. Firstly, divide image sets into c subsets, and divide the images in all the subsets into image blocks of 4×4. Then, simulate images in sets as a form of image blocks, dividing...
Sparse representation based classification (SRC) has been introduced as a new algorithm for face recognition classification instead of the classical gradient-based algorithms. However, there are some limitations that influence the robustness properties in SRC. One of the most effective parameters that impacts the SRC performance is the directory of training samples. It should contain enough samples...
This paper aims to present a novel method for automatic target recognition based on synthetic aperture radar (SAR) images. In order to describe a region of interest (target area), we use a saliency attention model. Then, the produced saliency map is used as a mask on SAR image in order to separate the ground target from the background. After that, we calculate the scale invariant feature transform...
This article proposes “Hexpo”, an activation function that has ability to scale the gradient and hence overcome the vanishing gradient problem. Unlike rectified linear units family which produces identity mapping on positive inputs, Hexpo has scalable limits on both positive and negative values. With parametrization, the active domain of Hexpo and the output it maps to is flexible. Thus it can alleviate...
In this paper, we propose a deep convolutional neural network model for in-bed behavior recognition and bed-exit prediction. This model extracts features for training from depth images taken by depth cameras in two categories: in-bed images taken several time intervals before a patient gets out of bed, and usual in-bed activity images. The depth camera-based model features grayscale and low-resolution...
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.