Machine Vision Inspection Systems, Machine Learning-Based Approaches. Группа авторов

1.9 Classification result by applying kNN technique.Figure 1.10 Classification result by applying NB technique.Figure 1.11 Classification result by applying LR technique.Figure 1.12 Classification result by applying NN technique.Figure 1.13 Classification result by applying kNN technique.Figure 1.14 Classification result by applying NB technique.Figure 1.15 Classification result by applying LR technique.Figure 1.16 Classification result by applying NN technique.Figure 1.17 Classification result by applying kNN technique.Figure 1.18 Classification result by applying NB technique.Figure 1.19 Classification result by applying LR technique.Figure 1.20 Classification result by applying NN technique.Figure 1.21 Classification result by applying kNN technique.Figure 1.22 Classification result by applying NB technique.Figure 1.23 Classification result by applying LR technique.Figure 1.24 Classification result by applying NN technique. Figure 1.25 Classification result by applying kNN technique.Figure 1.26 Classification result by applying NB technique.

      2 Chapter 2Figure 2.1 Siamese network architecture.Algorithm 1: Data generationFigure 2.2 Omniglot one-shot learning performance of Siamese networks.Figure 2.3 Sample 1 classification results.Figure 2.4 Sample 2 classification results.Figure 2.5 Omniglot n-shot n-way learning performance.Figure 2.6 Gurmukhi (left) and Cyrillic (right) alphabets.Figure 2.7 MNIST n-shot learning performance.

      3 Chapter 3Figure 3.1 Biconvex lens.Figure 3.2 Two lens imaging system.Figure 3.3 Extended 4f system.Figure 3.4 Image with a detected tumor cells.Figure 3.5 Reference image for detecting brain tumor cells.Figure 3.6 Uncorrelation peak indicating the severity of tumor.Figure 3.7 Correlation peak indicating the normal condition of the patient.

      4 Chapter 4Figure 4.1 Computer vision techniques.Figure 4.2 Types of machine learning algorithms.Figure 4.3 Feed forward neural networks.Figure 4.4 Back propagation neural networks.Figure 4.5 Proposed CNN architecture.Figure 4.6 Sigmoid and ReLU activation functions.Figure 4.7 FA% of proposed CNN models.Figure 4.8 Computer aided diagnostic system.

      5 Chapter 5Figure 5.1 Different areas of character recognition.Figure 5.2 Profiles of a skewed imageFigure 5.3 Skew corrected text region binarization.Figure 5.4 Character before and after thinning.Figure 5.5 Relation between different approaches of Recognition Systems.Figure 5.6 Holistic and analytic strategies.Figure 5.7 3-layered neural network.

      6 Chapter 6Figure 6.1 Knot sample images of seven types named as dry knot, encased knot, ho...Figure 6.2 Image augmentation (a) original image (b–c) augmented images with lab...Figure 6.3 Color feature component extracted from sample image.Figure 6.4 Texture feature component extracted from sample image.Figure 6.5 Minimum objective function values at particular iteration during trai...Figure 6.6 Graphical representation of confusion matrixFigure 6.7 Classification performance indices plot for testing samples.

      7 Chapter 7Figure 7.1 Text to speech system.Figure 7.2 UML Usecase diagram.Figure 7.3 Activity diagram for TTS system.Figure 7.4 Sub-activity diagram for pre-process moduleFigure 7.5 Deployment diagram.Figure 7.6 Python module requirements.Figure 7.7 Audio files and Metadata.txt.Figure 7.8 Audio files and transcriptions.Figure 7.9 Data preparation.Figure 7.10 Pre-process function for Tamil dataset.Figure 7.11 Function for Linear and Mel Spectrogram creation.Figure 7.12 Main function for Pre-process file.Figure 7.13 Set of valid symbols.Figure 7.14 Valid Tamil characters.Figure 7.15 Tacotron block diagram.Figure 7.16 CBHG module function.Figure 7.17 Code for character embedding and encoder.Figure 7.18 Code for attention module.Figure 7.19 Code for decoder.Figure 7.20 Code for Post-processing net.Figure 7.21 Training code.Figure 7.22 Train.py execution.Figure 7.23 Model initialization.Figure 7.24 Demo server code.Figure 7.25 Function to call synthesizer.Figure 7.26 Webpage script.Figure 7.27 Webpage script function call.Figure 7.28 Demo server execution.Figure 7.29 Webpage demo.Figure 7.30 Input to the model for audio synthesize.Figure 7.31 Audio output.

      8 Chapter 8Figure 8.1 The overall methodology of the present work.Figure 8.2 Methodology for optimizing the genetic algorithm.Figure 8.3 Working principle of decision tree.Figure 8.4 Linear regression graph plotted between two features.

      9 Chapter 9Figure 9.1 Mexican sign language alphabet. The letters (J, K, Ñ, Q, X, Z) that h...Figure 9.2 In pattern recognition, data is acquired through sensors. To learn an...Figure 9.3 For one data set, acquisition is performed using the leap motion sens...Figure 9.4 Setup for data acquisition using the leap motion controller. The sens...Figure 9.5 The metrics values are shown for each of the 21 letters of static alp...Figure 9.6 This plot shows the mean value of the metrics over the 21 letters of ...Figure 9.7 The metrics values are shown for each of the 21 letters of static alp...Figure 9.8 This plot shows the mean value of the metrics over the 21 letters of ...Figure 9.9 The metrics values are shown for each of the 21 letters of static alp...Figure 9.10 This plot shows the mean value of the metrics over the 21 letters of...Figure 9.11 The metrics values are shown for each of the 21 letters of static al...Figure 9.12 This plot shows the mean value of the metrics over the 21 letters of...Figure 9.13 The metrics values are shown for each of the 21 letters of static al...Figure 9.14 This plot shows the mean value of the metrics over the 21 letters of...Figure 9.15 The metrics values are shown for each of the 21 letters of static al...Figure 9.16 This plot shows the mean value of the metrics over the 21 letters of...Figure 9.17 The metrics values are shown for each of the 21 letters of static al...Figure 9.18 This plot shows the mean value of the metrics over the 21 letters of...Figure 9.19 The metrics values are shown for each of the 21 letters of static al...Figure 9.20 This plot shows the mean value of the metrics over the 21 letters of...Figure 9.21 The metrics values are shown for each of the 21 letters of static al...Figure 9.22 This plot shows the mean value of the metrics over the 21 letters of...

      10 Chapter 10Figure 10.1 Experimental process views of a SSBC.Figure 10.2 Schematic diagrams for SSBC.Figure 10.3 Exposed flow chart in solar cooker control based on adaptive and OSE...Figure 10.4 Shows sample analysis of 0.5% volume fractions act of parameters by ...Figure 10.5 Shown sample analysis of 10% volume fractions act of parameters by a...Figure 10.6 Shows 1 kg mass used in various volume fraction acts of SSBC by the ...Figure 10.7 Shows various volume fraction acts of SSBC and overall efficiency by...

      11 Chapter 11Figure 11.1 X ray tube: (a) stationary X-ray tube and (b) rotatory X-ray tube.Figure 11.2 (a): High SNR: large FOV images: MRI and (b): lower limb angiography...Figure 11.3 Medical applications of X-rays: (a) Chest PA, (b) Cervical spine Lat...Figure 11.4 Digital radiography machine: medical application.Figure 11.5 (a) Barium enema and (b) T-tube cholangiography.Figure 11.6 Computed tomography machine.Figure 11.7 Contrast brain angiography.Figure 11.8 Cardiac CT angiography.Figure 11.9 (a) CT abdomen angiography and (b) whole abdomen angiography reveali...

      12 Chapter