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.
This paper addresses an image-based tree recognition method using shape features and color features of leaf images. Our method requires two leaf images including a front leaf image and a rear leaf image which are placed on a white background. Firstly, a leaf region is automatically extracted using a graph cuts-based method. Next, sixteen shape features, six color features, and one size feature are...
By transforming each image to high-dimension data set and the nonlinear dimension reduction, the 1-dimension result on the structure of the data manifold is acquired, which can be used to describe the image sufficiently. Consequently, the recognition result will be translated into the 1-dimension result. That will greatly reduce the calculative complexity and the identification error, which comes...
This paper presents a view-independent hand pose recognition system, which allows the recognition of a limited set of predefined postures from single, low resolution depth images in real time on standard hardware in unconstrained environments. The system consists of three modules: hand segmentation and pose compensation, feature extraction and processing, and hand pose recognition. We use principal...
Handwritten text recognition is an active research area for many years. Handwritten text recognition needs to perform some preprocessing steps for better recognition. Initially, we find binary image of given handwritten text document and then after performing the line segmentation task on handwritten text document, we have to normalize to the segmented lines. There are various normalization task we...
Dorsal hand vein recognition is an emerging biometric technique researched today. In this paper, we propose a novel approach, the local feature-based ensemble 2-directional 2-dimensional linear discriminant analysis (LFBE(2D)2LDA), for dorsal hand vein recognition. The characteristic of the approach is to combine local and global information for vein recognition. First, we use block-based (2D)2PCA...
This paper proposes a detection method for electronic parts from electronic board images using HSV color format. In this study, we can pick out the electronic parts images by dividing the fixed section. If the parts have a low level of saturation, we detect only two colors that as black and white. To use this method, the detection rate of other colors is improved. It is possible to detect the region...
During a mealtimes, we usually enjoy not only eating itself but also having a conversation with other people together. Having a meal with our family or close friends is so enjoyable and an easy task because we already know each other. However we also have a chance to eat with acquaintances or totally new persons. In these cases, it is thought that the conversation would be difficult to continue because...
Multimodal eye recognition can improve the biometric systems recognition accuracy by combining iris and sclera recognition. However, poor quality images can significantly affect the system performance. In this paper, we proposed a quality fusion based multimodal eye recognition. Our quality measure evaluated the entire eye image quality, iris area quality, and sclera area quality. The experimental...
In this paper, we propose and implement a novel method for recognition static hand gestures using depth data from Kinect sensor of Microsoft. Compared to the entire human body, the hand is a smaller object with more complex articulations and more easily affected by segmentation errors. So it is a very challenging problem to recognize hand gestures. Our approach involves choosing HOG feature with both...
A facial recognition technique employing Frequency Domain Thresholding and Quantization (FD-TQ) is presented in this paper. The algorithm has attractive properties with respect to storage requirements and computational complexity in both the training and testing modes, which make the technique particularly suitable for large data bases. The new algorithm is applied to ORL, Yale and FERET data bases...
Facial recognition using spatial domain Diagonal Principal Component Analysis (DiaPCA) algorithm produces better accuracy compared to the Two Dimensional PCA (2DPCA). Transform Domain - 2DPCA (TD2DPCA) retains the high recognition accuracy of the 2DPCA while considerably reducing storage requirements and computational complexity. In this work, the Transform Domain PCA implementation of the DiaPCA...
Face detection and recognition has been introduced in many real world applications. Several algorithms have been implemented for either detection or recognition. In this paper, a novel algorithm, which simultaneously detects and recognizes facial images employing the same method, is presented. The proposed algorithm is based on a new 2D representation for the Histogram of Oriented Gradients (2D-HOG)...
This paper presents a Thai font type recognition on Thai document by using Scale-invariant feature transform (SIFT) . The features are extracted by Scale-invariant feature transform (SIFT) that is widely used in image processing. Sift is an algorithm for detecting local features in order to find similar objects. Our system contains ten fonts and ten text images in each font. We use ten text images...
In recent years, the drowsiness recognition is widely applied to the driver alerting or distance learning. The drowsiness recognition system is constructed on the basis of the recognition of eye states. The conventional methods for recognizing the eye states are often influenced by the illumination variations or hair/glasses occlusion. In this paper, we propose a new image feature called ¡§least correlated...
Facial expression analysis is essential to enable socially intelligent processing of multimedia video content. Most facial expression recognition algorithms generally analyze the whole image sequence of an expression to exploit its temporal characteristics. However, it is seldom studied whether it is necessary to utilize all the frames of a sequence, since human beings are able to capture the dynamics...
Most image and video retrieval tools used for large-scale media collections present query results as thumbnails arranged in a grid-like display with each thumbnail preserving the aspect ratio of its corresponding source image or video. Often, the outcome of a query is a set of thumbnails with different aspect ratios, thus a varying amount of padding space is used between the thumbnails in the display...
This paper presents a novel semi-supervised band selection technique for classification of the hyperspectral image. In our proposed method, a simple and efficient metric learning algorithm, i.e. relevant component analysis, is adopted for learning the whitening transformation matrix from which a feature metric is constructed for feature selection. This metric assesses both the class discrimination...
Many image processing techniques [1][2][3][8] and fuzzy algorithms [7][9][10] are applied in this research, such as color extraction, advanced morphology, particle filter, edge detection, membership function, fuzzification and defuzzification etc. The purpose of this paper is to show an image Morse code text input system based on real time mouth image recognition that provides the useful assistive...
To detect human sex from complex background, illumination variations and objects by machine is very difficult but important for adaptive information service. In this research, we present a preliminary design and experimental results of gender recognition from walking movements that utilizes gait energy image(GEI) with denoised energy image(DEI) pre-processing as support vector machine(SVM) classifier...
In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector comprises the outputs of a set of classifiers evaluated on the image. However, unlike traditional attributes which represent hand-selected object classes and predefined visual properties, our features are learned automatically...
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.