China
Africa
Explore chapters and articles related to this topic
Basic Approaches of Artificial Intelligence and Machine Learning in Thermal Image Processing
Published in U. Snekhalatha, K. Palani Thanaraj, Kurt Ammer, Artificial Intelligence-Based Infrared Thermal Image Processing and Its Applications, 2023
U. Snekhalatha, K. Palani Thanaraj, Kurt Ammer
The input image of size 128 × 128 × 3 is passed through the convolution layer where bytes normalization is followed by the application of the ReLU activation function, and then a convolution operation is executed on the feature maps. The ResNet V2 net contains three different types of inception modules, namely Inception ResNetA, Inception ResNetB, and Inception ResNetC. The inception modules help to generate discriminatory features and minimize the number of input parameters where each inception module consists of numerous convolutional and pooling layers in parallel. The feature maps obtained from the last inception layer are then passed through the GAP layer and an output of 2048 feature maps is obtained. Finally, three FCLs followed by the softmax layer are used to provide the classification (He et al., 2015).
Indoor Environment Assistance Navigation System Using Deep Convolutional Neural Networks
Published in Mohamed Lahby, Utku Kose, Akash Kumar Bhoi, Explainable Artificial Intelligence for Smart Cities, 2021
In our implementations we used the three versions of inception classifier, but the more robust with the best performances of classification was Inception v3 (Szegedy et al., 2015). It presents 42 layers; this inception version provides more computational efficiency with fewer parameters than its previous versions. This inception version makes lower error rate for image classification in ILSVRC (http://image-net.org/challenges/LSVRC/). Inception v3 is the enhanced inception architecture. It presents less number of parameters with more computational efficiencies. By reducing the number of parameters required for the deep CNN model we ensure that the network can go deeper. Inception v3 architecture presents a very promising inception category with different types of parameter optimization. In this pre-trained model a 5 × 5 convolution will be replaced by two 3 × 3 convolutions. When using a convolution layer with a convolution filter of 5 × 5, the number of parameters is set to 5 × 5 = 25, while by using 2 ∗ 3 × 3 filter we have 3 × 3 + 3 × 3 = 18. This technique reduces considerably the model’s complexity. This convolution operation reduces complexity and contributes for on block composing inception v3 architecture named ‘inception module A’. Figure 13.5 presents the inception module A architecture.
ApnaDermato: Human Skin Disease Finder Using Machine Learning
Published in Vishal Jain, Akash Tayal, Jaspreet Singh, Arun Solanki, Cognitive Computing Systems, 2021
Tarun Methwani, Gautam Menghani, Nitin Tejuja, Hemdev Karan, Raghani Madhu
Sourav et al. [8] used pretrained image recognizers for the identification of disease. They used the transfer learning concept; features and classification parts are reused and retrained, respectively, with the dataset. In transfer learning, the last layer is retrained for the dataset so that we can use it in our application. The system uses the Inception V3 and Inception Resnet V2 networks for feature extraction. In addition, learning algorithms for the training data are used. The MobileNet model is lightweight and performs computation faster. Hence, it can efficiently work with mobile applications. Depthwise convolution is the base for MobileNet architecture. Features are extracted using CNNs, and the classification part is done using a fully connected layer. Pretrained model Inception V3 gives good accuracy while being able to recognize around 1000 classes. It extracts the feature from the image and then classified based on features. The learning algorithms can predict some diseases with good accuracy. Inception V3 gives better results as compared to Inception Resnet V2 and MobileNet.
A Hybrid Feature Extraction and Classification using Xception-RF for Multiclass Disease Classification in Plant Leaves
Published in Applied Artificial Intelligence, 2023
Inception modules, which are found in convolutional neural networks, are said to represent a transitional stage between the depthwise separable convolution operation and the ordinary convolution, as stated in (Chollet 2017). When viewed in this light, a depthwise separable convolution can be interpreted as an Inception module consisting of the greatest possible number of towers. Based on this observation, a ground-breaking new architecture for deep convolutional neural networks that involve the replacement of Inception modules with depthwise separable convolutions is found. Howard et al. (2017) show that this architecture, which they call Xception, performs significantly better than Inception V3 on a larger image classification dataset that includes 350 million images and 17,000 classes. In our work, we have used an Xception network that has a pointwise convolution followed by a depthwise convolution. It was built with three phases, namely, entry, middle, and exit flow. Usually, an Xception model has 36 Conv layers, but we use the feature extraction part and vomit the classification layers since the classification is done by RF.
Enhancing deep learning techniques for the diagnosis of the novel coronavirus (COVID-19) using X-ray images
Published in Cogent Engineering, 2023
Maha Mesfer Meshref Alghamdi, Mohammed Yehia Hassan Dahab, Naael Homoud Abdulrahim Alazwary
An improved ResNet-50 CNN architecture called COVIDResNet was proposed in another study (Farooq & Hafeez, 2020). The experiment was conducted through increasingly re-sizing input images to 128 x 128 x 3, 224 x 224 x 3 and 229 x 229 x 3 pixels and selecting the automatic learning rate for fine-tuning the network at each stage. The results from the work showed high accuracy and computational efficiency for multi-class classification. In another study, a 24 layered CNN model for the classification of COVID-19 and normal images was developed by Panwar et al. (2020). The model was called nCOVnet, and the training of the model involved use of an X-ray data set. The model produced an accuracy of up to 97%. Zhang et al. (Zhang et al) developed a new deep learning supported anomaly detection model for COVID-19 using X-ray images. When the threshold was set to 0.25, their model produced a sensitivity of 90%, and a specificity of 87.84%. Similarly, another transfer learning-based CNN model for detecting COVID-19 was proposed by Narin et al. (2021). They used ResNet50, InceptionV3, and Inception-ResNetV2 pre-trained models for transfer learning. Their simulation results showed that the ResNet50-based model produced the best results. In the following section, we provide details of how our study, which focused on multiclass classification of COVID-19, was carried out.
Multimodal face shape detection based on human temperament with hybrid feature fusion and Inception V3 extraction model
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
Srinivas Adapa, Vamsidhar Enireddy
In the proposed approach, the Inception V3 model for feature extraction of video frames is used to extract intrinsic features from the region of the face (Tio 2019; Zahid et al. 2020; Dong et al. 2020). The Inception V3 model is a deep learning technique using a Convolution Neural Network (CNN) to categorizecategorise images. The Inception V3 is a more advanced version of the basic model Inception V1 model. It uses convolutions like 5 × 5, which reduce the input dimension by a large margin, causing the neural network to reduce some accuracy. Therefore, the Inception V3 model is proposed for real-time video feature extraction. It is also said to be a GoogLeNet network that adopts an inception network framework that not only diminishes the count of network parameters but also improves the depth of the network. Therefore, it is mostly used in image classification problems. There are various versions of the inception network, such as Inception V1, Inception V2, Inception V3, Inception V4, and Inception-ResNet. The Inception V3 network comprises the convolution layer, max-pooling layer, and average pooling layer. These layers are also used in extracting the intrinsic features. Most commonly, the Inception V3 model is used for extracting features and is also utilizedutilised in detecting objects, tracking objects in human pose estimation, segmentation, and classification of video and super-resolution. Figure 4 represents the feature extraction for video frames using the Inception V3 model and RPCA to reduce dimensionality in extracted features.