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.
In this study, we propose a two-stage method for material segmentation in hyperspectral images. The first stage employs a Convolutional Neural Network (CNN) to predict the material label at individual pixels. The second stage further refines the segmentation by a fully-connected Conditional Random Field (CRF) framework. For the first stage, we experimented with two different network architectures...
Since road markings are one of the main landmarks used for traffic guidance, perceiving them may be a crucial task for autonomous vehicles. In visual approaches, road marking detection consists in detecting pixels of an image that corresponds to a road marking. Recently, most approaches have aimed on detecting lane markings only, and few of them proposed methods to detect other types of road markings...
The quality of life of people is increasing together with the developing technologies. One of the most important factors affecting daily life is smart cities. The quality of life of people is positively affected by emerging this concept in recent years. Autonomous vehicles confront with the term of the smart city and have become even more popular in recent years. In this study, a system of traffic...
The present work proposes to recognize the static hand gestures taken under invariations features as scale, rotation, translation, illumination, noise and background. We use the alphabet of sign language of Peru (LSP). For this purpose, digital image processing techniques are used to eliminate or reduce noise, to improve the contrast under a variant illumination, to separate the hand from the background...
We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms. Specifically, our architecture combines i) a Haar wavelet-based tree-like convolutional neural network (CNN), ii) a random layer realizing a radial basis function kernel approximation, and iii) a linear classifier. While stages...
Ultrasound image is one of the modalities that is widely used to examine the abnormality of thyroid gland since it is relatively low-cost and safety. Fine needle aspiration biopsy (FNAB) is usually used by radiologists to determine the thyroid nodule whether malignant or benign. Commonly, malignancy of thyroid nodule determined based on shape feature. This research proposes a scheme for classifying...
Temporal segmentation of facial expressions in video sequences is an important and relatively unexplored problem in facial image analysis. The difficulties of temporal segmentation include irregular facial behavior, large variability in facial gestures and moderate to large head motion. To solve those problems, we propose a two-step method to segment facial expression temporally, which consists of...
One of recent trends [31, 32, 14] in network architecture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more efficient than a large kernel, given the same computational complexity. However, in the field of semantic segmentation, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive...
We present a new image feature detection method. Our method selects features based on segmenting points with high local intensity variations across different scales using a robust rank order statistics approach. Our method produces a large number of repeatable features that are invariant to several image transformations such as rotation, scaling, viewpoint, and lighting variations. We show the advantages...
The given work describes a new technique of image segmentation, in particular for building detection on radar or infrared Earth-observation images. The method is based on property of most man-made objects which consist in straight edges and mostly right angles. The developed 2D adaptive image filter assists to detect straight edges even if given image fragment has a low contrast and has been extremely...
In this paper we propose a new method for scene representation and recognition based on the concept of Region Subspaces. Each image is pre-segmented into semantically meaningful regions and local features are extracted at different scales from each such region. The Region Subspaces are the low-dimensional linear subspaces calculated from the set of local features inside each region. We also define...
Deep convolutional neural networks (DCNNs) have been employed in many computer vision tasks with great success due to their robustness in feature learning. One of the advantages of DCNNs is their representation robustness to object locations, which is useful for object recognition tasks. However, this also discards spatial information, which is useful when dealing with topological information of the...
This paper introduces automatic framework brain tumor detection, which detects and classify brain tumor in MR imaging. The proposed framework brain tumor detection is an important tool to detect the tumor and differentiate between patients that diagnosis as certain brain tumor and probable brain tumor due to its ability to measure regional changes features in the brain that reflect disease progression...
Segmentation of MR images is more important and is an essential process in resolving the human tissues, especially at the time of clinical analysis. Brain tissue is explicitly complex and it consists of three normal main tissues named White Matter (WM), Gray Matter (GM) and Cerebral Spinal Fluid (CSF) and abnormal tissues like tumor and edema. These normal and abnormal tissues can be detected using...
Soft computing in the field of agriculture science is being employed with computer vision techniques in order to detect the diseases in crops to increase the overall yield. A Modified Rotation Kernel Transformation(MRKT) based directional feature extraction scheme is presents to resolve the issues occurring due to shape, color or other deceptive features during plant disease recognition. The MRKT...
This paper presents a novel framework for brain tumor diagnosis and its grade classification based on higher order statistical texture features namely kurtosis and skewness along with selected morphological features. These features were extracted from segmented tumorous T2-weighted brain MR images, in order to distinguish high grade (HG) tumor from low grade (LG) tumor. Tumor classification is carried...
The brain is one of the vital organ of the body where it is the custodian of the involuntary and voluntary actions like walking, vision, memory. Now a days the most common brain disorders are Alzheimer's disease, Epilepsy (paralysis or stroke), tumors, brain tumors. Early diagnosis and proper treatment of brain tumors is required. The Computer Aided Diagnostic tools (CAD) can be used by the doctor...
An innovative and robust image segmentation approach has been proposed for magnetic resonance (MR) brain tumor extraction. We have proposed a novel technique to classify a given MR brain image as benign or malignant. In order to extract the features from given MR brain tumor image, we have first employed wavelet transform which is then followed by Laplacian Eigen maps (LE) so as to curtail the dimensions...
This paper proposes a new approach to recognize iris from distantly acquired facial images by utilizing multiple feature descriptors and classifiers. Firstly, Log-Gabor (LG), Contourlet Transform (CT), Gradient Local Auto-Correlation (GLAC) and Convolutional Neural Network (CNN) descriptors are employed on segmented normalized iris image and contextual eye image to extract features. Then, K-Nearest...
Breast cancer is the second leading cause of cancer death in women according to World Health Organization (WHO). Development of computer aided diagnostic (CAD) systems has great importance as a secondary reader systems for a correct diagnosis and treatment process. In this paper, a deep learning based feature extraction method by convolutional neural network (CNN) is proposed for automated mitosis...
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.