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.
An approach that is rooted in psychological and biological research is suggested for extracting object contours. The approach combine high level object recognition cues with low-level image edges to obtain the object contour. We argue for a top-down bottom-up interaction architecture by demonstrating an automated two-stage object detection program that first plausibly identifies the object using an...
From the series of digital X-ray images we extracted bone edges using information entropy based edge detection algorithms. The extracted edges are series of two dimensional coordinates from image space. The space series were tested for shapes of medical interest inside the knee joint. In particular, the existence of straight edges inside the knee joint was tested for by using digital filtering and...
In this paper, a simple and efficient algorithm for detecting deformed and occlusion triangular and circular traffic signs under complex natural scenes is proposed. Firstly, the image is segmented and binarized. Then the convex hull of every contour extracted from the binarized image is calculated. Some concave part of a contour is removed and is replaced by the corresponding convex edge of the convex...
We propose a fast technique for concealment of transmission errors in images. Corrupted regions are restored by texture extrapolation from the surrounding regions logically associated through image segmentation. Areas in the image containing unsharp edges or gradients, which are difficult to segment properly, are the main problem producing artefacts in the result. Therefore, our approach utilizes...
Engineering of the compiled software is an important task in software engineering. One of the stages of the engineering technologies is a construction and analysis of a control flow graphs, which reflect a general structure of algorithms. The paper presents a technique for analyzing and visualizing the control flow graph of a compiled software. The analysis is based on semantically equivalent transformations...
The Hough Transform is a popular tool for feature detection in digital image processing due to its robustness to noise and missing data. However, the computational cost associated to its voting scheme has prevented software implementation to achieve real time performance. This paper demonstrates the parallel computing power of Graphics Processing Unit (GPU) in area of image processing. In this paper,...
Retinal diseases are fatal and if not detected and treated during the early stages itself might result in the loss of eyesight. The true retinal artifacts can be distinguished using Scanning laser ophthalmoscopes (SLOs) is an important task for premature retinal detection. The importance of using SLO is which can image a wide part of the retina for better diagnosis of the retinal artifacts. The artifacts...
A major cause of deaths among the elderly relates to accidental falls. Such falls are of particular medical concern to this population because they often result in severe injuries, since senior citizens usually live alone and cannot ask for help when accidents happen. In this paper, we propose a fall detection system with the help of a Gaussian mixture background model to build the background before...
This paper proposes a new method for the segmentation of the scanned point clouds that achieves an accurate definition of objects' faces, critical for their digitalization. The topological structuring of the input point cloud is realised by a nearest-neighbour graph, while locally fitted surfaces are used to quantify the objects' shapes. Noise is filtered by a graph-cut and the segmentation is performed...
To conserve and manage fish stocks in fisheries, people monitor the growth and quantities of fish by collected underwater videos and images. However, the efficiency of finding fish from videos and images is limited by manual operation. In this paper, we propose an automatic method to improve the efficiency of finding fish by shape matching. In our method, a segmentation method, Segmentation by Aggregating...
Autonomous Underwater Vehicle docking technology is now extensively used in the field of underwater. Vision guidance, as one of its core components, shows a great development prospect. In this paper, a brief description of the vision guidance models and the previous algorithm were described. Both the advantages and disadvantages of that algorithm would be analyzed. By using grey-scale feature analysis,...
A set of image processing approaches are proposed for processing digital holographic images of plankton. The images are segmented to produce regions of interest (ROI) of plankton, and then the shape description of plankton is normalized which is invariant under the transformations of translation, scaling, skewing and rotation. Also break points of the normalized shape contour curve are detected and...
Thinning is an important pre-processing step in many shape based character and word recognition systems. The one-pixel wide thinned character image is useful for identifying the shape of various strokes used to from the character, which is helpful in many applications such as word spotting in the document image, content-based document image retrieval, character and word classification, etc. However,...
The paper proposes a dynamic shape context retrieval algorithm based on statistic. It selects shape's feature point's number dynamically, and statistics the number of target shape's feature points in different area block to form a contour feature point histogram. Finally, measuring the similarity is used dynamic programming algorithm. This method can selects the number of feature points adaptively,...
The proposed algorithm is designed to detect the boundary of a region which can be identified by some characteristic feature at a general level, but heterogeneity within the region itself prevents the use of standard gradient techniques. The general principle of the algorithm is based on inner boundary tracing and involves three techniques- Technique of Tracing, Technique for Convex Turns and Technique...
A novel multi-criteria optimization framework for matching of partially visible shapes in multiple images using joint geometric graph embedding is proposed. The proposed framework achieves matching of partial shapes in images that exhibit extreme variations in scale, orientation, viewpoint and illumination and also instances of occlusion; conditions which render impractical the use of global contour-based...
A method for automatic detection or recognition using high-frequency forward-looking imaging sonar is proposed. The method includes segmentation of an underwater object's echo shape or its acoustic shadow shape. For accuracy of segmentation, some constraints were assumed on the underwater ground and the sonar's pose. The separated shape was compared to simulated reference shapes to know its orientation...
The work is devoted to the problem of weld segmentation in modern methods for evaluating the quality of welds. One of the methods of the weld quality evaluation is visual inspection. This work deals with the possibility of implementing algorithms of recognition and evaluation of welds using visual system in single-board computers. Result of this paper is computing time comparison of chosen embedded...
Image and video processing is a very important topic for research in the world. Its application pervade in the whole world, as perceived in video surveillance, anomaly detection, human action analysis etc. Nevertheless some drawbacks are there, as there is large storage required for storing the data and retrieval of a particular data and from the colossal storage it is very difficult or in some case...
With the enhancement of the technologies in medical sciences, it is becoming necessary to trace the object of interest, so need of boundary tracing techniques is increased. This paper provides a survey on graph based segmentation techniques which aim at extracting the boundary of object.
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.