Image Feature Extraction and Object Recognition Based on Vision Neural Mechanism

2019 ◽  
Vol 34 (06) ◽  
pp. 2054017 ◽  
Author(s):  
Peng Cheng Wei ◽  
Yang Zou
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Object Recognition ◽  
Visual Information ◽  
Neural Mechanism ◽  
Image Features ◽  
Image Feature ◽  
Training Samples ◽  
Computer Vision Technology ◽  
Processing Of Visual Information

As an important branch of artificial intelligence, computer vision plays a huge role in the rapid development of artificial intelligence. From a biological point of view, in the acquisition and processing of information, vision is much more important than hearing, touch, etc., because 70% of the human cerebral cortex is processing visual information. Therefore, advances in computer vision technology are critical to the development of artificial intelligence that is designed to allow machines to think and handle things like humans. The acquisition and processing of visual information has always been the focus of computer vision research, and it is also difficult. The main problem of traditional computer vision technology in the processing of visual information is that the extracted image features are less discriminative, the generalization ability of image features in complex background scenes is insufficient, and the recognition ability on object recognition is poor. In response to these problems, based on the visual neural mechanism, this paper establishes an appropriate computer model for the neuronal cells in the human primary visual cortex, models the recognition response mechanism of the visual ventral system, and performs image feature extraction on the training samples. And object recognition. The results show that compared with the traditional methods, the proposed method effectively improves the discrimination of image features, and the image features extracted under complex background scenes have good generalization ability. On this basis, the training samples can be effectively recognized. The results show that the model based on the visual neural mechanism, the recognition of the edge, orientation and contour of the training sample show the advantages of the biological vision mechanism in object recognition.

Data Analyzing via Probabilistic Modeling

2021 ◽  
pp. 25-51
Author(s):  
Dariusz Jacek Jakóbczak
Keyword(s):  
Artificial Intelligence ◽  
Image Processing ◽  
Computer Vision ◽  
Object Recognition ◽  
Computer Science ◽  
Classical Problem ◽  
Contour Reconstruction ◽  
Curve Interpolation ◽  
Characteristic Features ◽  
Unknown Object

Object recognition is one of the topics of artificial intelligence, computer vision, image processing, and machine vision. The classical problem in these areas of computer science is that of determining object via characteristic features. An important feature of the object is its contour. Accurate reconstruction of contour points leads to possibility to compare the unknown object with models of specified objects. The key information about the object is the set of contour points which are treated as interpolation nodes. Classical interpolations (Lagrange or Newton polynomials) are useless for precise reconstruction of the contour. The chapter is dealing with proposed method of contour reconstruction via curves interpolation. First stage consists in computing the contour points of the object to be recognized. Then one can compare models of known objects, given by the sets of contour points, with coordinates of interpolated points of unknown object. Contour points reconstruction and curve interpolation are possible using a new method of Hurwitz-Radon matrices.

scholarly journals An Improved Smart Traffic Signal using Computer Vision and Artificial Intelligence

2019 ◽  
Vol 8 (4) ◽  
pp. 4124-4131
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Traffic Safety ◽  
Intelligent Transportation Systems ◽  
Traffic Monitoring ◽  
Transportation Systems ◽  
Traffic Signal ◽  
Traffic Light ◽  
Traffic System ◽  
Computer Vision Technology

The growth in population all over the world and in particular in India causes an increase in the number of vehicles which, create complications regarding traffic jam and traffic safety. The primary solution to recover the jam condition is the expansion of capacities of roads by building new streets. However, this requires extra efforts and more time that is a costly and ineffective solution. Therefore, there is a need for alternative solution methodologies that are being implemented. Intelligent traffic monitoring is a branch of intelligent transportation systems that focuses on improving traffic signal conditions. The key goal of such an intelligent monitoring system is to improve the traffic system in a way that reduces delays. Many cities facing these delays because of the inefficient configuration of traffic light systems which are mostly fixed-cycle protocol based. Therefore, there is a profound need to improve and automate these traffic light systems. The establishment of a mixed technique of artificial intelligence (AI) and computer vision (CV) can be desirable to develop an authenticated and scalable traffic system which can aid to solve such problems. Proposed work supports the use of computer vision technology to build a resource-efficient, synchronous and automated traffic analysis. Video samples were collected from multiple areas to use in the system. The system applied and the vehicle was counted and classified into different classes. Manually and automatically annotated patterns were used for the classification. The multi-reference-line mechanism employed to find the speed of the vehicle and analyze traffic. The system makes its decision based on a number of vehicles, backwards-forward synchronous data and emergency conditions.

scholarly journals A survey on computer vision technology in Camera Based ETA devices

2015 ◽  
Vol 1 (3) ◽  
pp. 115
Author(s):  
Amir Ramezani Dooraki
Keyword(s):  
Computer Vision ◽  
Object Recognition ◽  
Computer Science ◽  
Stereo Vision ◽  
Visually Impaired ◽  
High Potential ◽  
Methods And Techniques ◽  
Computer Vision Technology ◽  
Visually Impaired Persons ◽  
Vision Technique

Electronic Travel Aid systems are expected to make impaired persons able to perform their everyday tasks such as finding an object and avoiding obstacles easier. Among ETA devices, Camera Based ETA devices are the new one and with a high potential for helping Visually Impaired Persons. With recent advances in computer science and specially computer vision, Camera Based ETA devices used several computer vision algorithms and techniques such as object recognition and stereo vision in order to help VIP to perform tasks such as reading banknotes, recognizing people and avoiding obstacles. This paper analyses and appraises a number of literatures in this area with focus on stereo vision technique. Finally, after discussing about the methods and techniques used in different literatures, it is concluded that the stereo vision is the best technique for helping VIP in their everyday navigation.

DISCRIMINATORY SPARSE CODING AND ITS APPLICATION TO FACE RECOGNITION

2003 ◽  
Vol 03 (03) ◽  
pp. 503-521
Author(s):  
JUN SUN ◽  
WENYUAN WANG ◽  
QING ZHUO ◽  
CHENGYUAN MA
Keyword(s):  
Feature Extraction ◽  
Sparse Coding ◽  
Recognition Performance ◽  
Classification Performance ◽  
Image Features ◽  
Face Image ◽  
Image Feature ◽  
Training Samples ◽  
The Subject ◽  
Independent Features

Feature extraction is very important in the subject of pattern recognition. Sparse coding is an approach for extracting the independent features of an image. The image features extracted by sparse coding have led to better recognition performance as compared to those from traditional PCA-based methods. A new discriminatory sparse coding (DSC) algorithm is proposed in this paper to further improve the classification performance. Based on reinforcement learning, DSC encodes the training samples by individual class rather than by individual image as in sparse coding. Having done that it will produce a set of features with large and small intraclass variations, which is very suitable for recognition tasks. Experiments are performed on face image feature extraction and recognition. Compared with the traditional PCA- and ICA-based methods, DSC shows a much better recognition performance.

Object Recognition via Contour Points Reconstruction Using Hurwitz - Radon Matrices

2013 ◽  
pp. 998-1018
Author(s):  
Dariusz Jakóbczak
Keyword(s):  
Artificial Intelligence ◽  
Image Processing ◽  
Computer Vision ◽  
Object Recognition ◽  
Computer Science ◽  
Classical Problem ◽  
Contour Reconstruction ◽  
Curve Interpolation ◽  
Characteristic Features ◽  
Unknown Object

Object recognition is one of the topics of artificial intelligence, computer vision, image processing and machine vision. The classical problem in these areas of computer science is that of determining object via characteristic features. Important feature of the object is its contour. Accurate reconstruction of contour points leads to possibility to compare the unknown object with models of specified objects. The key information about the object is the set of contour points which are treated as interpolation nodes. Classical interpolations (Lagrange or Newton polynomials) are useless for precise reconstruction of the contour. The chapter is dealing with proposed method of contour reconstruction via curves interpolation. First stage consists in computing the contour points of the object to be recognized. Then one can compare models of known objects, given by the sets of contour points, with coordinates of interpolated points of unknown object. Contour points reconstruction and curve interpolation is possible using new method of Hurwitz - Radon Matrices.

Object Recognition via Contour Points Reconstruction Using Hurwitz - Radon Matrices

2011 ◽  
pp. 87-107 ◽  
Author(s):  
Dariusz Jakóbczak
Keyword(s):  
Artificial Intelligence ◽  
Image Processing ◽  
Computer Vision ◽  
Object Recognition ◽  
Computer Science ◽  
Classical Problem ◽  
Contour Reconstruction ◽  
Curve Interpolation ◽  
Characteristic Features ◽  
Unknown Object

Object recognition is one of the topics of artificial intelligence, computer vision, image processing and machine vision. The classical problem in these areas of computer science is that of determining object via characteristic features. Important feature of the object is its contour. Accurate reconstruction of contour points leads to possibility to compare the unknown object with models of specified objects. The key information about the object is the set of contour points which are treated as interpolation nodes. Classical interpolations (Lagrange or Newton polynomials) are useless for precise reconstruction of the contour. The chapter is dealing with proposed method of contour reconstruction via curves interpolation. First stage consists in computing the contour points of the object to be recognized. Then one can compare models of known objects, given by the sets of contour points, with coordinates of interpolated points of unknown object. Contour points reconstruction and curve interpolation is possible using new method of Hurwitz - Radon Matrices.

A cloud integrated strategy for reconfigurable manufacturing systems

2020 ◽  
Vol 28 (4) ◽  
pp. 305-318
Author(s):  
Bo Guo ◽  
Fu-Shin Lee ◽  
Chen-I Lin ◽  
Yun-Qing Lu
Keyword(s):  
Visual Information ◽  
Data Exchange ◽  
Manufacturing Systems ◽  
Industrial Robot ◽  
Image Features ◽  
Cnc Machining ◽  
Image Feature ◽  
Control Panel ◽  
Manufacturing Resources ◽  
Cnc Controller

Manufacturing industries nowadays need to reconfigure their production lines promptly as to acclimate to rapid changing markets. Meanwhile, exercising system reconfigurations also needs to manage innumerous types of manufacturing apparatus involved. Nevertheless, traditional incompatible manufacturing systems delivered by exclusive vendors usually increase manufacture costs and prolong development time. This paper presents a novel RMS framework, which is intended to implement a Redis master/slave server mechanism to integrate various CNC manufacturing apparatus, hardware control means, and data exchange protocols through developed configurating codes. In the RMS framework each manufacturing apparatus or accessory stands for an object, and information of recognized CNC control panel image features, associated apparatus tuned parameters, communication formats, operation procedures, and control APIs, are stored into the Redis master cloud server database. Through implementation of machine vision techniques to acquire CNC controller panel images, the system effectively identifies instantaneous CNC machining states and response messages once the embedded image features are recognized. Upon demanding system reconfigurations for the manufacturing resources, the system issues commands from Redis local client servers to retrieve the stored information in the Redis master cloud servers, in which the resources for registered CNC machines, robots, and built-in accessories are maintained securely. The system then exploits the collected information locally to reconfigure involved manufacturing resources and starts manufacturing immediately, and thus is capable to promptly response to fast revised orders in a comitative market. In a prototyped RMS architecture, the proposed approach takes advantage of recognized feedback visual information, which is obtained using an invariant image feature extraction algorithm, and effectively commands an industrial robot to accomplish demanded actions on a CNC control panel, as a regular operator does daily in front of the CNC machine for manufacturing.

Counterfactual Autoencoder for Unsupervised Semantic Learning

2020 ◽  
pp. 720-736
Author(s):  
Saad Sadiq ◽  
Mei-Ling Shyu ◽  
Daniel J. Feaster
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Language Processing ◽  
Speech Processing ◽  
Semantic Learning ◽  
Novel Approach ◽  
Training Samples ◽  
Latent Space

Deep Neural Networks (DNNs) are best known for being the state-of-the-art in artificial intelligence (AI) applications including natural language processing (NLP), speech processing, computer vision, etc. In spite of all recent achievements of deep learning, it has yet to achieve semantic learning required to reason about the data. This lack of reasoning is partially imputed to the boorish memorization of patterns and curves from millions of training samples and ignoring the spatiotemporal relationships. The proposed framework puts forward a novel approach based on variational autoencoders (VAEs) by using the potential outcomes model and developing the counterfactual autoencoders. The proposed framework transforms any sort of multimedia input distributions to a meaningful latent space while giving more control over how the latent space is created. This allows us to model data that is better suited to answer inference-based queries, which is very valuable in reasoning-based AI applications.

scholarly journals Biologically-Inspired Computational Neural Mechanism for Human Action/activity Recognition: A Review

Electronics ◽  
2019 ◽  
Vol 8 (10) ◽  
pp. 1169
Author(s):  
Bardia Yousefi ◽  
Chu Kiong Loo
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Activity Recognition ◽  
Computational Models ◽  
Neural Mechanism ◽  
Human Action ◽  
Action Perception ◽  
Biologically Inspired ◽  
Knowledge Based ◽  
Massive Information

Theoretical neuroscience investigation shows valuable information on the mechanism for recognizing the biological movements in the mammalian visual system. This involves many different fields of researches such as psychological, neurophysiology, neuro-psychological, computer vision, and artificial intelligence (AI). The research on these areas provided massive information and plausible computational models. Here, a review on this subject is presented. This paper describes different perspective to look at this task including action perception, computational and knowledge based modeling, psychological, and neuroscience approaches.

Sign in / Sign up

Export Citation Format

Share Document