Figure 2 - available via license: Creative Commons Attribution 3.0 Unported
Content may be subject to copyright.
Download
View publication
The structure of a typical Deep Learning model.

The structure of a typical Deep Learning model.

Source publication
Figure 1. Three classes of tomato in scale of 100 × 100 pixels.
Figure 2. The structure of a typical Deep Learning model.
Figure 3. The structure of Convolutional Neural Networks.
Figure 4. Architecture of VGG16 model which consists of 16 layers.
Classifying maturity of cherry tomatoes using Deep Transfer Learning techniques
Article
Full-text available
  • Mar 2021
This research studies a method to classify the tomatoes’ maturity by using deep transfer learning techniques. We carry out sorting systems adopting three pre-trained convolutional neural networks of VGG16, VGG19, and ResNet101. The experimental results show that the VGG19 model obtains a high precision on both the train set and the test set.
Cite
Download full-text

Context in source publication

Context 1
... Neural Networks (CNNs) are some types of Deep Learning (DL) models. The fundamental structure of DL model is illustrated in Figure 2. Here, the input the input í µí²™ = [í µí²™ í µí¿ , í µí²™ í µí¿ , . . ...

Similar publications

FIG. 2. Structure of proposed Wav2KWS model. A backbone network is...
Characteristics of Google Speech Command Datasets V1 and V2 used in...
Accuracy of baseline models and proposed Wav2KWS model on Google Speech...
Accuracy of baseline models and proposed Wav2KWS model on Google Speech...
+1 Accuracy of baseline models and proposed Wav2KWS model considering 25...
Wav2KWS: Transfer Learning From Speech Representations for Keyword Spotting
Article
Full-text available
  • May 2021
With the expanding development of on-device artificial intelligence, voice-enabled devices such as smart speakers, wearables, and other on-device or edge processing systems have been proposed. However, building or obtaining large training datasets that are essential for robust keyword spotting (KWS) remains cumbersome. To address this problem, we p...
View
Fig. 1. General schema for the used network, an Inception-ResNet-v2...
Fig. 3. Plot of samples' body locations.
Fig. 4. Some HAM10000 images resized with OpenCV.
Fig. 5. Accuracy and Loss for each epoch.
+2 Fig. 6. Two of the minority classes, Actinic Keratoses (akiec) and...
Skin Cancer Classification using Inception Network and Transfer Learning
Preprint
Full-text available
  • Nov 2021
Medical data classification is typically a challenging task due to imbalance between classes. In this paper, we propose an approach to classify dermatoscopic images from HAM10000 (Human Against Machine with 10000 training images) dataset, consisting of seven imbalanced types of skin lesions, with good precision and low resources requirements. Class...
View
Figure 3: Structure diagram of residual block
Figure 4: ResNet-50 structure chart
Figure 5: The central idea of transfer learning
Figure 6: Two strategies for transfer learning
+8 Figure 9: Confounding matrix of BP neural network
Classification of Domestic Refuse in Medical Institutions Based on Transfer Learning and Convolutional Neural Network
Article
Full-text available
  • Jan 2021
The problem of domestic refuse is becoming more and more serious with the use of all kinds of equipment in medical institutions. This matter arouses people's attention. Traditional artificial waste classification is subjective and cannot be put accurately; moreover, the working environment of sorting is poor and the efficiency is low. Therefore, au...
View
Fig. 1. Inspection model architecture.
Fig. 2. Damaged gear during preparation steps.
Fig. 3. Raspberry Pi 3 microcomputer (left) and the camera board (right).
Fig. 4. Used light-box for data gathering.
+2 Fig. 5. Some of the evaluation images.
Effect of Environmental Factors on the Accuracy of a Quality Inspection System Based on Transfer Learning
Article
Full-text available
  • Jun 2021
In this research, a study is introduced on the effect of several environmental factors on the performance of an already constructed quality inspection system, which was designed using a transfer learning approach based on convolutional neural networks. The system comprised two sets of layers, transferred layers set from an already trained model (De...
View
Fig. 8 shows the (a)original images and their corresponding (b)ground...
Model parameters and their corresponding values
Mean Absolute Error comparison (400 homogeneous
Mean Absolute Error (heterogeneous input images)
The average error metrics over the entire test dataset for architectures
CNN Based Monocular Depth Estimation
Article
Full-text available
  • Jan 2021
In several applications, such as scene interpretation and reconstruction, precise depth measurement from images is a significant challenge. Current depth estimate techniques frequently provide fuzzy, low-resolution estimates. With the use of transfer learning, this research executes a convolutional neural network for generating a high-resolution de...
View