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.
The mineral separation efficiency of flotation process depends very much on the surface properties of feed ore and addition of chemical reagents. Machine vision based analysis of froth appearance is considered as an indication of flotation performance. Bubble structure obtained by watershed segmentation scheme is used to determine the amount of reagent. To explore bubble size distribution, nonparametric...
In this paper, we propose an unsupervised method of playfield segmentation for various sport videos. The method first applies local maximum clustering to gather feature samples into several clusters in the Cb-Cr plane. Next, a novel idea is developed to merge clusters into four color classes - Red, Green, Blue and Grey. Finally, a simple scheme of region fusion eliminates small and unimportant areas...
According to the correlation and statistical information of neighboring pixels in image, a statistical morphological predict operator is constructed based on the Markov random field theory, and the corresponding 2-D statistical morphological wavelet is also defined. Under the conditional probability density function in MRF model, It can be proved that more detail coefficients approach to zero after...
Inconsistency in light source direction resulted from image forgery is one of the traces which cannot be removed. Hereby, a blind identification to distinguish the image authenticity by detecting inconsistency in light source direction was proposed. The search means and least-squares method were used to calculate the light source direction for local and infinite light source images respectively, in...
Relevance feedback is a good method for the semantic gap between the low-level similarity and the high-level user's query in content-based image retrieval. It interactively asks user whether certain proposed images and the query output are relevant or not. In this paper we propose the use of a support vector machines for conducting effective relevance feedback for trademark retrieval. The algorithm...
There are many situations in which an object that needs to be grasped is not graspable, but could be grasped if it was situated at a different location. By applying nonprehensile manipulation actions such as poking, the object can be moved to a new location without first being grasped. We consider these issues in the context of an artificial cognitive system. The goal of the paper is twofold; firstly,...
Approximate solutions to labelling problems can be found using binary graph cuts and either the ??-?? expansion or ??-?? swap algorithms. In some specific cases, an exact solution can be computed by constructing a multilabel graph. However, in many practical applications the multilabel graph construction is infeasible due to its excessively large memory requirements. In this work, we expand the concept...
The success of visual tracking systems is highly dependent upon the effectiveness of the measurement function used to evaluate the likelihood of a hypothesized object state. Generative tracking algorithms attempt to find the global and other local maxima of these measurement functions. As such, designing measurement functions which have a small number of local maxima is highly desirable. Edge based...
In this paper, a diffusion mechanism for encrypting data in the electronic code book (ECB) mode is introduced. Our diffusion mechanism treats the encryption leakages of the ECB mode by using a substitution/permutation network (SPN), which diffuses the bytes of the data together before encryption. The tests were made on AES and RC6 block ciphers implemented in the ECB mode pre-processed with our mechanism...
We propose a technique to classify characters by two different forms of their symmetry features. The generalized symmetry transform is applied to digits from the USPS data set. These features are then used to train probabilistic neural networks and their performances are compared to the traditional method.
File carving is a digital forensic technique which data files are extracted from unstructured data sources without the information of the previously stored file system. Since JPEG is one of the most popular image formats in the storage and distribution of digital photographic imagery, JPEG carving aroused numerous researchers' great interest. In this paper, a new algorithm of reassembling the fragmented...
In this paper an automatic multilevel thresholding approach, based on binary particle swarm optimization, is proposed. The proposed approach automatically determines the "optimum" number of the thresholds and simultaneously searches the optimal thresholds, by optimizing a function which uses the gray level thresholds as parameters. The algorithm starts with large number initial thresholds,...
Image holes can be a direct refection of digital image complexity. We propose a hole counting formula for binary images which is the microscopical exhibition of image hole nature. Based on image Euler Number formula, the formula is proved and a new approach is proposed to count image holes. Our intensive experiments show the correctness of the hole counting formula and the feasibility of the approach.
A novel method of watermarking in image spatial domains is proposed in this paper. The level transformation previously proposed for embedding watermark bits into each pixel of a source image is used adaptively with estimating the resulting subjective image quality. Thus, a desired subjective quality can be achieved on the watermarked image. First, the measurements of image quality by subjective evaluations...
Braille is the most common means of reading and study for visually handicapped people. The need for converting Braille documents into a computer-readable format has motivated research into the implementation of Braille recognition systems. The most fundamental steps in such recognition are estimating the scaling, spacing, and skewness properties of a given Braille document. In this paper we propose...
A number of action recognition methods make use of spatio-temporal features. These features often consist of local spatio-temporal descriptors centered at locations provided by an interest point detector. The extracted descriptors will then serve as input to classification algorithms. The correct scale of these descriptors is an essential parameter to be determined. Improved information quality has...
This paper proposes an effective lane detection and tracking method using statistical modeling of lane color and edge-orientation in the image sequence. At first, we will address some problem of classifying a pixel into two classes(lane or background) and detecting one exact lane. Generally, the probability of a pixel classification error conditioned on the distinctive feature vector can be decreased...
A gamma-distributed texture in coherent imagery is widely applied on some fields such as description of texture characteristic and verification of classification algorithm. In this paper, a method based on spherically invariant random process for texture modeling in SAR imagery has been proposed, and the feasibility of modeling for gamma-distributed texture with SIRP is testified, the representation...
In this work an ignorance-based fuzzy clustering algorithm is presented. The algorithm is based on the entropy-based clustering algorithm proposed by Yao et al.. In our proposal, we calculate the total ignorance instead of using the entropy at each data point to select the data point as the first cluster center. The experimental results show that the ignorance-based clustering improves the data classification...
In this paper, we experimental investigate if the current reversible data hiding schemes are detectable. By modeling the distributions of horizontal pixel difference of natural image using generalized Gaussian model, we find that the horizontal difference histogram of watermarked image is significantly altered. Furthermore, the difference between the horizontal and the vertical difference histogram...
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.