An automated approach for developing a Convolutional Neural Network using a modified Firefly algorithm for Image ClassificationConvolutional neural network (CNN) is a basic configuration of neural networks that can perform deep learning. There are many applications based on CNN in fields of image ...
The classification of high-resolution and remote sensed terrain images with high accuracy is one of the greatest challenges in machine learning. In the present study, a novel CNN feature reduction using Wavelet Entropy Optimized with Genetic Algorithm (GA-WEE-CNN) method was used for remote sensing...
Full size image It is known to us that convolutional neural network (CNN)8 is one of the most effective model architectures for image classification. Many CNN based network frameworks have been proposed, such as AlexNet9 and ZFNet10 with fewer convolutional layers, and others with deeper layers...
classification using MFCC. From the difference between Mel frequency scale sub-bands energies, a new vector is built and the performance of the K-nearest neighbor is tested using this newly built vector. For HMM, 99.5% accuracy is obtained for the speaker-dependent case, whereas the accuracy ...
(CNN) and recurrent neural networks (RNN) are examples of DL models widely used for these tasks. Image preprocessing methods often precede the process flow of CNN, followed by the convolutional-pooling operation, which detects suggestive features that lead to the classification of the image as ...
The Convolutional Neural Network (CNN) is the most popular network for image analysis, data analysis, and classification problems [25,31]. Generally, CNN is an artificial neural network that specializes in being able to pick or detect patterns and make sense of them. Pattern detection makes CNN...
tiling, normalization,resolution reduction, stain normalization,ROI detection,morphological operation, etc. used commonly. Pre-processing methods regulate brightness and contrast variations in the image and suppress noise. This provides ease of operation forclassification algorithmsthat are very sensitive to ...
The algorithm first performs data preprocessing of image compression, difference, resise, and normalization on the image. Then it uses the CNN model to extract the tamper feature, finally completes the calculation and classification of the fully connected layer feature data through SVM, and builds ...
In this paper, we demonstrate our new learning method using some popular DL models (U-Net22, DCN23) and Mask R-CNN17 for the ant detection problem. Pseudo-labels/annotations Annotations for classification/detection/segmentation tasks usually refer to the image-/object-/pixel-wise ground truth ...
The CNNGenetic project has a single module named gacnn.py which has a class named GACNN for training CNN using GA.The project can be used for classification problems where only 1 class per sample is allowed.PyGAD is an open-source Python library for building the genetic algorithm and ...