WiMi Developed a BPR-based CNN Image Classification Technology to Better Solve the Image Classification Problems
- New image classification method achieves higher classification performance than traditional methods
- None.
Convolutional Neural Network (CNN) is a deep learning model specialized for processing images. It can automatically extract features from an image through convolution and pooling operations and perform classification using fully connected layers. Convolutional operations involve applying a convolutional kernel (also known as a filter) to each position on the image and outputting the result as a feature map. Pooling operation means down-sampling the feature map to reduce the amount of computation and risk of overfitting.
In traditional CNN image recognition classification models, the softmax function is used for classification. softmax function converts a set of scores into a probability distribution, where each score represents the confidence score that the image belongs to a certain category. Traditional pattern recognition methods usually use hyperplanes in the feature space to segment categories. However, this approach has some downsides, such as the need to manually select features and the difficulty in handling nonlinear data. On the contrary, BPR can overcome these problems by performing class recognition through geometric cover sets that are concatenated in a high-dimensional feature space.
BPR is a bionic-based pattern recognition method, the basic idea of which is to simulate the processing of sensory information using biological systems, and to view the pattern recognition process as taking place in a high-dimensional feature space. In this high-dimensional space, each sample point is regarded as an object rather than a point. Therefore, different classes of samples are distributed in different regions of the high-dimensional feature space, and these regions are called geometric coverage sets. Each geometric covering set consists of a set of geometric objects, which are called geometric primitives, e.g., spheres, cones, polyhedra, etc. By appropriate combinations of geometric primitives, coverage sets with high classification performance can be constructed to enable the recognition of categories.
WiMi combines BPR with CNN to achieve better image classification results. Specifically, CNN image classification based on BPR can map CNN features into a high-dimensional feature space and construct a geometric coverage set in that space, and then display new samples in that space and determine the class they belong to.
WiMi BPR-based CNN image classification uses a mapping function to display CNN features in a high-dimensional feature space. This function can be a simple nonlinear transform such as a polynomial transform or a radial basis function (RBF) transform. It is also possible to learn this mapping function using some more complex functions such as a neural network or a support vector machine (SVM) to transform the CNN features into a form that is easier to classify in the high-dimensional feature space.
This image classification technique has been shown to have high classification performance in high-dimensional feature spaces with geometric primitives, such as spheres, cones or polyhedra, to construct geometric coverage sets. Optimization algorithms, such as genetic algorithms or particle swarm optimization algorithms, can be used to search for the optimal combination of geometric primitives to construct the best geometric coverage set. Finally, a classifier, such as a K-nearest neighbor algorithm or an SVM, is used to identify the class to which the new sample belongs.
The specific way to realize the image classification that combines BPR with CNN is as follows:
Preparation of training and test dataset: a dataset containing images of many different categories needs to be collected. This dataset should contain two parts: the training dataset and the test dataset. The training dataset is used to train the CNN model and the test dataset is used to test the performance of the classifier.
Training CNN model and extracting image features: a CNN model is trained using the training dataset and the features of each image are extracted using the model. These features will be used to construct a geometric coverage set in a high-dimensional feature space.
Mapping CNN features into high-dimensional feature space: a mapping function needs to be used to map the CNN features into the high-dimensional feature space. This mapping function can be learned using some nonlinear transforms such as polynomial transforms or RBF transforms, or using more complex functions such as neural networks or SVMs.
Constructing geometric coverage sets: geometric coverage sets are constructed using some geometric primitives that have been shown to have high classification performance in high-dimensional feature spaces, such as spheres, cones, or polyhedra. Then, we can use some optimization algorithms, such as genetic algorithms or particle swarm optimization algorithms, to search for the optimal combination of geometric primitives to construct the best geometric coverage set.
Classifying new samples: a classifier, such as a K-nearest neighbor algorithm or SVM, is used to identify the category to which the new sample belongs. We can map the features of the new sample into a high-dimensional feature space, then find the nearest geometric cover set in that space, and finally classify the new sample into the category represented by the cover set.
This image classification technique is characterized by combining CNN and BPR to classify images by constructing geometric cover sets in a high-dimensional feature space. Compared to the current traditional CNN model using the softmax function for classification, the softmax function has limited capacity and cannot well handle complex classification problems, such as image classification. In addition, the CNN model cannot fully utilize the geometric structure of the high-dimensional feature space, and thus cannot achieve optimal classification performance. As well, traditional pattern recognition methods usually require manual selection of features and classifiers, which requires a lot of labor and time costs. By combining BPR and CNN, this technique can overcome some of the shortcomings of traditional pattern recognition, improve the performance of image classification, and can handle complex image classification problems. This method in image classification can overcome some of the current shortcomings of traditional pattern recognition as well as in most cases, higher classification performance than traditional methods. And it can deal with complex image classification problems, such as image recognition, target detection and image segmentation.
At present, the image classification technology based on CNN has been widely used in many fields, and the method of WiMi combined with BPR can overcome the limitations of traditional pattern recognition methods and improve the accuracy and reliability of image classification. It is believed that with the continuous development and progress of technology, this technology will have wider applications and more outstanding performance in the future.
About WIMI Hologram Cloud
WIMI Hologram Cloud, Inc. (NASDAQ:WIMI) is a holographic cloud comprehensive technical solution provider that focuses on professional areas including holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, holographic car navigation and others. Its services and holographic AR technologies include holographic AR automotive application, 3D holographic pulse LiDAR technology, holographic vision semiconductor technology, holographic software development, holographic AR advertising technology, holographic AR entertainment technology, holographic ARSDK payment, interactive holographic communication and other holographic AR technologies.
Safe Harbor Statements
This press release contains "forward-looking statements" within the Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as "will," "expects," "anticipates," "future," "intends," "plans," "believes," "estimates," and similar statements. Statements that are not historical facts, including statements about the Company's beliefs and expectations, are forward-looking statements. Among other things, the business outlook and quotations from management in this press release and the Company's strategic and operational plans contain forward−looking statements. The Company may also make written or oral forward−looking statements in its periodic reports to the US Securities and Exchange Commission ("SEC") on Forms 20−F and 6−K, in its annual report to shareholders, in press releases, and other written materials, and in oral statements made by its officers, directors or employees to third parties. Forward-looking statements involve inherent risks and uncertainties. Several factors could cause actual results to differ materially from those contained in any forward−looking statement, including but not limited to the following: the Company's goals and strategies; the Company's future business development, financial condition, and results of operations; the expected growth of the AR holographic industry; and the Company's expectations regarding demand for and market acceptance of its products and services.
Further information regarding these and other risks is included in the Company's annual report on Form 20-F and the current report on Form 6-K and other documents filed with the SEC. All information provided in this press release is as of the date of this press release. The Company does not undertake any obligation to update any forward-looking statement except as required under applicable laws.
View original content:https://www.prnewswire.com/news-releases/wimi-developed-a-bpr-based-cnn-image-classification-technology-to-better-solve-the-image-classification-problems-301907801.html
SOURCE WiMi Hologram Cloud Inc.
