Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “image object recognition”

Image analysis and object recognition

P K Thiruvikraman · 2024

This chapter deals with various algorithms and techniques used for image analysis and object recognition. We start by discussing simple 'masks' which are used to detect points and lines in an image, before taking up the Hough transform. Various techniques for segmentation, such as edge detection, and thresholding are discussed in detail. Many techniques such as Signature, chain code, statistical moments. Skeltonization, principal component analysis which are used for description and representation of images are discussed in detail together with some applications. The chapter ends with a discussion on pattern recognition using clustering techniques.

Cited by 0

Image Dataset for Object Recognition

ICub Facility · Figshare · 2018

Subset of the "iCubWorld Transformations" dataset (https://robotology.github.io/iCubWorld/) to be used for the Deep Learning hands-on session at the Winter School on Humanoid Robot Programming (http://www.icub.org/winterschool/).

Cited by 0Open access

Object Recognition using Still Image

Deepika T.V, Stafford Michahial, Dr M Shiva kumar · IJARCCE · 2016

Detection of objects in cluttered scenes is a fundamental challenge that has only recently been widely undertaken by computer vision systems. This paper proposes a novel method how to detect a particular object in cluttered scenes, given a reference image of the object. This paper presents an algorithm for detecting a specific object based on finding point correspondences between the reference and the target image. It can detect objects despite a scale change or in-plane rotation. It is also robust to small amount of out-of-plane rotation and conclusion.

Cited by 1Open access

Image reduction for object recognition

Ben-Zion Shaick, Leonid Yaroslavsky · 2003

The problem addressed is that of the fast generation of accurate multiple downscaled copies of an input image, with an arbitrary non-integer reduction factor, for object detection and recognition. Three algorithms that can be implemented in parallel, recursive and hybrid architectures are introduced and compared in terms of their accuracy and computational complexity. It is shown that the recursive algorithm is the most advantageous in terms of computational complexity, while the parallel algorithm performs better in terms of accuracy reduction. The hybrid algorithm combines advantages of both.

Cited by 3

Object Recognition Using Image Segmentation

Manish Chaturvedi, Mandeep Kaur, Nitin Rakesh et al. · 2020

The aim of the paper is to develop a system that can recognize various targeted objects in real-time by incorporating some computer vision techniques and advanced boosted Machine Learning algorithms to solve the problem of object recognition with high accuracy. The task of object detection is a combination of both, image classification and image localization. Image classification identifies the class of target object whereas localization identifies its position inside the input image. Viola-Jones is an algorithm that can work effectively for recognizing a large number of categories such as airplanes, cars, faces, etc. It works on feature extraction and uses Haar-Like features to achieve the objective. So, Viola-J ones is the algorithm that will be used for the development purpose of this paper. Also, instead of using a normal image, the image segmentation technique will be used to create segments in the image that will make it easy to analyze and process the image for further computations.

Cited by 5

Image Dataset for Object Recognition

ICub Facility · Figshare · 2018

Subset of the "iCubWorld Transformations" dataset (https://robotology.github.io/iCubWorld/) to be used for the Deep Learning hands-on session at the Winter School on Humanoid Robot Programming (http://www.icub.org/winterschool/).

Cited by 0Open access

Efficient Object Recognition and Image Retrieval

John Jaesung Lee, Trevor J. Darrell, John Jaesung Lee · 2008

Algorithms for recognition and retrieval tasks generally call for both speed and accu-racy. When scaling up to very large applications, however, we encounter additional significant requirements: adaptability and scalability. In many real-world systems, large numbers of images are constantly added to the database, requiring the algo-rithm to quickly tune itself to recent trends so it can serve queries more effectively. Moreover, the systems need to be able to meet the demands of simultaneous queries from many users. In this thesis, I describe two new algorithms intended to meet these requirements and give an extensive experimental evaluation for both. The first algorithm constructs an adaptive vocabulary forest, which is an efficient image-database model that grows and shrinks as needed while adapting its structure to tune itself to recent trends. The second algorithm is a method for efficiently performing classification tasks by comparing query images to only a fixed number of training examples, regardless of

Cited by 0

Object Recognition Algorithm of Sonar Image

Xiaodong Tian, Dechao Zhou, Zhong Liu · 2006

In the target detection and recognition of underwater sonar image, object recognition is one of key technologies. With analysis and calculation, three features which have good distinguish degree are chosen to construct feature vector for classification, clustering method, neural network and support vector machine were presented. Correct classification ratio can be above 95%. Simulation result indicates that features presented in this paper have characteristics such as precision and robustness, which reduce dependence of classifying result on classifier

Cited by 3

Approaches to Invariant Image Object Recognition

Diplomarbeit Im Fach Informatik, Lehrstuhl Informatik, Vi Mathematisch-naturwissenschaftliche et al. · 2008

This work had not been possible without the many helpful suggestions, discussions and assistances it received from various of people. I would especially like to thank Prof. Dr.-Ing. Hermann Ney and Dipl.-Inform. J"org Dahmen for the fruitful conversations and their interest in the work. Their ideas and suggestions were a great help. I would like to thank Prof. Dr. Walter Oberschelp as well, who kindly accepted to attend the work and brought to my attention the interesting subject of the holographic classifier. Furthermore, I would like to thank the other student members of the image recognition group at the Chair of Computer Science VI, who were always there to discuss things and give helpful comments and tips, namely Alexander Cr"amer, Mark Oliver G"uld, Ralf Perrey and Thomas Theiner.

Cited by 0

Color image processing and object recognition

A. Moghaddamzadeh · 1995

Object recognition is the process of identifying an object from its image. Before any identification process can begin the color image must be processed. By processing the color image of an object, different areas would be separated from each other. Features of the isolated areas can then be extracted and compared to the learned objects in the system data base and the best match found. Object recognition has applications in robotics vision, obstacle and goal identifications, product classification, industrial quality control, and visual inspection and diagnosis. After a digital color image is grabbed or scanned, it must be smoothed to remove external noises, especially the ones associated with the camera or scanner. Edge detection is performed on the smoothed image to separate areas or segments from each other. The edge information is used in conjunction with the smoothed image for segmentation. In the segmented image, each segment belongs to only one object and has an enclosed contour. Features are then extracted and segment contours coded. The best fitting straight or curve lines are then found. Objects in the data base are then compared to the extracted lines and features using graph theory and the best match is found. Fuzzy operators and thresholds were used throughout this work to propagate uncertainties and delay decision makings for later stages.

Cited by 1

Object Detection and Recognition in Image

Muzikářová, Michaela · Brno University of Technology Digital Library (Brno University of Technology) · 2015

Tato bakalářská práce se zabývá návrhem a implementací aplikace typu klient-server, která umožňuje rozpoznání objektů v obraze a využívá již existující mobilní aplikaci. V teoretické části jsou nejprve popsány rozdíly lidského a počítačového vidění, dále detekce a rozpoznání objektů včetně vybraných metod. Další sekce obsahuje popis umělých neuronových sítí, které byly pro práci hlouběji nastudovány, spolu s jejich využitím k rozpoznání objektů. Následují informace, týkající se vybraných mobilních aplikací pro rozpoznání objektů v obraze, zakončené přehledem frameworků a knihoven, umožňujících práci s neuronovými sítěmi. Z nich byl k práci zvolen Caffe Framework. Dále je popsán průběh návrhu a řešení a vytvořený systém včetně experimentů a datasetů, použitých k ověření jeho funkčnosti.

Cited by 0

DEVELOPING IMAGE OBJECT RECOGNITION SYSTEMS USING OBJECT-ORIENTED TECHNIQUE

Atr State · 2001

The problem of developing image object recognition systems is concerned from the viewpoint of software engineering. Some difficulties and their causes in develeping an application are summarized. The idea and the way of using object-oriented technique to analyze and design recognition systems are proposed. And an object recognition system on remote sensing images implemented by this way is introduced.

Cited by 0