Conventional imaging systems have the pixels that are arranged in the regular lattice positions, or lattice pixel placement (LPP). LPP is employed in most imaging systems for its advantages on pixel read-out and image reconstruction ways, however, in LPP, the clarity on image representation depends on the direction of the object in the image, or the directional dependency exists. In this paper,...

In this article we outline a method that automatically transforms an Euclidean ornament into a hyperbolic one. The necessary steps are pattern recognition, symmetry detection, extraction of a Euclidean fundamental region, conformal deformation to a hyperbolic fundamental region and tessellation of the hyperbolic plane with this patch. Each of these steps has its own mathematical subtleties that...

We present a technique for performing segmentation of macroscopic three-dimensional objects recorded using in-line digital holography. We numerically reconstruct a single perspective of each object at a range of depths. At each point in the digital wavefront we calculate variance about a neighborhood. The maximum variance at each point over all depths is thresholded to classify it as an object ...

While playing soccer, the main task of the robot vision system is identifying and tracking objects such as ball, goals, teammate robots and opponent robots. The basis of many object identification methods, particularly those in soccer robots and RoboCup environment, is using algorithms based on pixel color properties. One of the major problems of these robots in RoboCup environment is changes i...

We present a model-based technique for encoding nonrigid object classes in terms of object prototypes. Objects from the same class can be parameterized by identifying shape and appearance invariants of the class to devise lowlevel representations. The approach presented here creates a flexible model for an object class from a set of prototypes. This model is then used to estimate the parameters...

This paper presents a novel segmentation method for identifying mass regions in mammograms. This work is a part of an on-going project whose aim is to build a Computer-Aided Diagnosis (CADx) system that classifies suspicious cancer masses in mammograms as benign or malignant. Segmentation of suspicious mass regions is an important pre-processing step to achieve high accuracy results, because th...

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which a...

Based on implementing target tracking by means of particle filtering, a technique framework of tracking target by integrating particle filtering and background modeling is presented. The multi-target tracking (MTT) is classified into 5 modules as background modeling, multi-target tracking, initializing, re-initializing and particle filtering. Firstly, the author models each pixel of the image w...

Computing object distance using image processing is an important research area in the field of computer vision and robot navigation applications. In this paper we have proposed a new method to compute the distance of an object using a single image. According to our observation there exists a relationship between the physical distance of an object and its pixel height. We exploit this relationsh...