Abstract
This paper studies the traditional target classification and recognition algorithm based on Histogram of Oriented Gradients (HOG) feature extraction and Support Vector Machine (SVM) classification and applies this algorithm to distributed artificial intelligence image recognition. Due to the huge number of images, the general detection speed cannot meet the requirements. We have improved the HOG feature extraction algorithm. Using principal component analysis (PCA) to perform dimensionality reduction operations on HOG features and doing distributed artificial intelligence image recognition experiments, the results show that the image detection efficiency is slightly improved, and the detection speed is also improved. This article analyzes the reason for these changes because PCA mainly uses the useful feature information in HOG features. The parallelization processing of HOG features on graphics processing unit (GPU) is studied. GPU is used for high parallel and high-density calculations, and the calculation of HOG features is very complicated. Using GPU for parallelization of HOG features can make the calculation speed of HOG features improved. We use image experiments for the parallelized HOG feature algorithm. Experimental simulations show that the speed of distributed artificial intelligence image recognition is greatly improved. By analyzing the existing digital image recognition methods, an improved BP neural network algorithm is proposed. Under the premise of ensuring accuracy, the recognition speed of digital images is accelerated, the time required for recognition is reduced, real-time performance is guaranteed, and the effectiveness of the algorithm is verified.
Highlights
With the rapid development of communication technology and computer technology, emerging services such as cloud computing, the Internet of ings, and social networks have promoted the growth of data types and scales in human society at an unprecedented rate [1]
Using graphics processing unit (GPU)-based principle operations and CUDA kernel functions, the statistics of the gradient histogram is divided into two stages: in the first stage, we calculate the gradient histogram of the data corresponding to each parallel thread block, because the execution of each thread block is mutually exclusive, so we can calculate the gradient histogram in shared memory. e second stage is to add each element on the temporary gradient histogram of the thread block to the final gradient histogram. e specific method we implemented to allocate parallel resources is as follows: a thread block in CUDA corresponds to a cell in the Histogram of Oriented Gradients (HOG) feature extraction algorithm
Because the current HOG feature extraction algorithm consumes a lot of time, and there are a lot of redundant features, the current algorithm has low detection accuracy and detection efficiency for the detection target. is paper proposes to use GPU and central processing unit (CPU) parallelism to improve the existing algorithm. is article introduces the principles and implementation steps of algorithms such as HOG feature, Support Vector Machine (SVM), and principal component analysis (PCA) and conducts experiments on distributed artificial intelligence image recognition based on HOG feature extraction and SVM classification
Summary
With the rapid development of communication technology and computer technology, emerging services such as cloud computing, the Internet of ings, and social networks have promoted the growth of data types and scales in human society at an unprecedented rate [1]. As a new distributed computing technology, multiagent system has developed rapidly since its appearance It has become a way of thinking and tools for complex system analysis and simulation and has gradually penetrated into medical services, smart cities, power systems, national defense construction, etc. This article proposes to use GPU to accelerate HOG in parallel, introduces the principle architecture and working mechanism of GPU, conducts research on the parallelization algorithm of HOG feature extraction, and conducts experimental analysis on distributed artificial intelligence image recognition. E PCA algorithm reduces the dimension of the weight matrix between the input layer and the hidden layer and minimizes the number of neurons in the hidden layer, which is verified by experiments It can be seen from the experimental results that this algorithm achieves the effect of improving the training speed under the premise of ensuring the accuracy of the digital image
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
