Computational strategies for object recognition
نویسندگان
چکیده
منابع مشابه
a computational visual neuroscience model for object recognition
in this study with the inspirations from both neuroscience and computer science, a combinatorial framework for object recognition was proposed having benefited from the advantages of both biologically-inspired hmax_s architecture model for feature extraction and extreme learning machine (elm) as a classifier. hmax model is a feed-forward hierarchical structure resembling the ventral pathway in ...
متن کاملComputational Models for Object Detection and Recognition
Object Detection and Recognition, being a fundamental problem in Computer Vision, is receiving increased importance these days. The motivation for this is its application in wide spectrum of fields like Video Summarization, Content Based Retrieval , Manufacturing, Inspection and Surveillance. This paper gives an overview of algorithms existing for object detection and recognition and their perf...
متن کاملLearning Control Strategies for Object Recognition
This paper presents a system for learning object-speciic recognition strategies from training images and libraries of image understanding routines. The motivation for this work is that thirty years of computer vision research has produced hundreds of algorithms for visual subtasks ranging from edge detection to pose determination, but very few complete vision systems. The Schema Learning System...
متن کاملA framework for integrating object recognition strategies
Genehmigte Dissertation zur Erlangung des akademischen Grades Doktorin der Ingenieurwissenschaften (Dr.-Ing.). While preparing this thesis more people than I can mentoin here accompanied and supported me whom I want to thank a lot. Special thanks go to my supervisor Gerhard Sagerer who gave me the chance of working in the area of scientific computer science and manages the difficult tightrope w...
متن کاملComputational theories of object recognition.
This paper examines four current theoretical approaches to the representation and recognition of visual objects: structural descriptions, geometric constraints, multidimensional feature spaces and shape-space approximation. The strengths and weaknesses of the four theories are considered, with a special focus on their approach to categorization - a computationally challenging task which is not ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Computing Surveys
سال: 1992
ISSN: 0360-0300,1557-7341
DOI: 10.1145/128762.128763