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 paper we explore ways to address the issue of dataset bias in person re-identification by using data augmentation to increase the variability of the available datasets, and we introduce a novel data augmentation method for re-identification based on changing the image background. We show that use of data augmentation can improve the cross-dataset generalisation of convolutional network based...
Content Based Video Classification is becoming necessary for various video analysis applications to be able to handle humongous amounts of video data being generated & shared all over the Internet. This paper proposes use of DTTBTC for color based feature extraction from video key frames which are used by machine learning classifiers for training & testing. Experimental results show accuracy...
The objective of this paper is to evaluate Bag-of-Colors (BoC) descriptor for land use classification. BoC can be used either as a global or local descriptor. In this paper we present and evaluate both approaches. We analyze the influence of different parameters on classification accuracy and introduce a modification of descriptor extraction process, which significantly influences the classification...
This paper proposes a novel algorithm for Content Based Scene Retrieval (CBSR) using video features such as moment, histogram, Edge Histogram Descriptor (EHD)… This application is similar for Content Based Image Retrieval (CBIR) but instead of finding corresponding images in the database, it identifies the corresponding scene which contains the testing frame. The proposed algorithm can deal with scene...
This paper proposes an automated non-invasive system for skin cancer (melanoma) detection based on Support Vector Machine classification. The proposed system uses a number of features extracted from the Wavelet or the Curvelet decomposition of the grayscale skin lesion images and color features obtained from the original color images. The dataset used include both digital images and Dermoscopy images...
In this paper, we present an approach for image-based surface classification using multi-class Support Vector Machine (SVM). Classifying surfaces in aerial images is an important step towards an increased aircraft autonomy in emergency landing situations. We design a one-vs-all SVM classifier and conduct experiments on five data sets. Results demonstrate consistent overall performance figures over...
This paper discussed a proposed method to detect fire with the main focus is to extract the fire features to increase the accuracy and using LBP-TOP feature extraction scheme to accelerate the process. The fire features produced by LBP-TOP was modeled by using dustering K-Means method as the reference model when the classification process was done by using K-NN method. By using those methods, the...
In this paper, we try to develop a natural user interface for interactive TV, which is more natural and easy to use with a webcam and the fingers of user. We analyze the images captured by the camera settled on the screen and track any fingers of the users. After the fingers were tracked, users can control the TV by the gestures. We invited several user to participate the testing of the system. The...
In digital image forensics, camera model identification seeks for the source camera model information from the given images under investigation. To achieve this goal, one of the popular approaches is extracting from the images under investigation certain statistical features that capture the difference caused by camera structure and various in-camera image processing algorithms, followed by machine...
In this paper, a compensatory neurofuzzy inference system (CNIS) is proposed for classification applications. The compensatory-based fuzzy reasoning method using adaptive fuzzy operations of neurofuzzy inference systems makes fuzzy logic systems more adaptive and effective. Furthermore, an online learning algorithm is proposed to automatically construct the CNIS model. They are created and adapted...
People with color blindness often have difficulty in distinguishing certain colors. People with total color blindness can only see things in black, white, and gray. Deficiency of color perception is causing many problems for people with color blindness, from daily activities to educational issue. One solution to help this problem is to build an aid system using image processing techniques and applying...
In order to more accurately detect drusen and vessel from retinal fundus images, we proposed a set of new features and presented a learning based detection scheme. These features are designed to describe the variation patterns of image's local geometrical structure across various scales. Theoretical analysis and a series of preliminary experimental results demonstrate the extra ability and high accuracy...
This paper presents a study of cell-phone camera model linkage that matches digital images against potential makes / models of cell-phone camera sources using camera color interpolation features. The matching performance is examined and the dependency on the content of training image collection is evaluated via variance analysis. Training content dependency can be dealt with under the framework of...
This paper discusses the application of two unsupervised methods in classifying type of soils. Soils that are suitable for agricultural activities can be classified into four classes which are hill soil, organic soil, alteration soil and alluvium soil. In addition, no specific support system is able to classify the type of soil and retrieve the information for location and suitable plants for local...
There is an increasing need for automatically segmenting the regions of different landforms from a multispectral satellite image. The problem of Landform classification using data only from a 3-band optical sensor (IRS-series), in the absence of DEM (Digital Elevation Model) data, is complex due to overlapping and confusing spectral reflectance from several different landform classes. We propose a...
In this paper, the digital watermarking based on modification of image pixels is presented with two new concepts to enhance the accuracy of extracted watermark. By embedding the watermark into a low pixels variation channel in CIELAB color space and using adaptive pixel replacement technique in the watermark extraction process, the accuracy of recovered signal can be improved. Sets of experiment are...
The performance of assistive communication brain-computer interfaces has been studied mostly for languages with alphabetic script. The viability of using such systems for languages with other types of script, such as Chinese, which has a logographic script, is currently poorly understood. Here, a performance analysis of the P300 Speller is presented for Chinese text input. The performance of six distinct...
Exploring the possibility of using technology for grain quality classification is necessary for the consumer market to protect consumers who are susceptible to any form of contamination that may occur in the market. Although some research has been reported on the classification of paddy seeds, no published work is found on the classification of milled rice which is the principal food in many countries...
We present a framework for developing a color transformation between two display devices to achieve a desired perceptual match. The framework is realized by first developing an optimal color transformation between the two devices, and then formulating an optimization problem to develop a hardware resource-constrained approximation to the optimal transformation. We employ the framework to investigate...
A method for improving the watermark extraction performance of the digital watermarking based on the modification of image pixels is proposed in this paper. By embedding the watermark in the chrominance channel and using the Weiner filter with 3times3 window size in the watermark extraction process, the accuracy of the extracted watermark can be improved. Sets of experiment are carried out to prove...
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.