Computer Vision is the technology of the present and the future. Specialize with this program and achieve the professional progress you are looking for" 

In recent years, artificial intelligence has brought about a great revolution in the technological world. It has allowed for the development of software and machines that are capable of learning, generating new knowledge and acting according to the best available solution in each case. As such, its applications range from computational sciences, through research in areas such as healthcare, to the development of tools such as vehicles, robots or video games. 

It is a field in continuous expansion and is already fundamental in most computer and technology companies. However, precisely because of its great importance and momentum in recent years, specialties have been emerging that focus on one of its specific aspects. Computer Vision is one of the most important of these. This focuses on how machines process the visual information received and how that information can be used, either to improve the machine's own relationship with its own environment by making its operations more accurate, or to collect data efficiently. 

For this reason, it is a fundamental field and is closely related to Machine Learning, so more and more companies are looking for computer scientists specialized in this field who can provide the best technological solutions in the development of computer vision projects. This Professional master’s degree offers an in-depth study of this field, bringing you closer to the most innovative knowledge and tools so that, upon completion of the program, you can make immediate professional progress thanks to your new competencies. 

And all this will be achieved by following TECH Global University's 100% online methodology, specially designed so that working computer scientists and engineers can balance this program with their jobs, since it adapts to their personal circumstances. In addition, students will be accompanied throughout the learning process by an expert teaching staff and will enjoy the best multimedia teaching resources such as case studies, technical videos, master classes or interactive summaries, among many others. 

The future is already here. Do not miss the opportunity and become a leading expert in Computer Vision thanks to this Professional master’s degree"

This Professional master’s degree in Computer Vision contains the most complete and up-to-date educational program on the market. Its most notable features are:

• The development of case studies presented by experts in computer science and computer vision
• The graphic, schematic, and practical contents with which they are created, provide scientific and practical information on the disciplines that are essential for professional practice
• Practical exercises where self-assessment can be used to improve learning
• Its special emphasis on innovative methodologies
• Theoretical lessons, questions to the expert, debate forums on controversial topics, and individual reflection assignments 
• Content that is accessible from any fixed or portable device with an Internet connection

Do not wait any longer and specialize in a key area of future technology that will make you advance professionally immediately" 

The program’s teaching staff includes professionals from the sector who contribute their work experience to this educational program, as well as renowned specialists from leading societies and prestigious universities. 

The multimedia content, developed with the latest educational technology, will provide the professional with situated and contextual learning, i.e., a simulated environment that will provide immersive education programmed to learn in real situations. 

This program is designed around Problem-Based Learning, whereby the professional must try to solve the different professional practice situations that arise during the academic year. This will be done with the help of an innovative system of interactive videos made by renowned experts. 

Delve into artificial intelligence and Deep Learning and become a reference in the field of Computer Vision"

Enroll now and start developing promising computer vision projects with what you will learn in this program"

The contents of this Professional master’s degree in Computer Vision have been designed by leading international experts in the field, so that computer scientists will have access to highly specialized knowledge that will place him as a reference in the field. Therefore, in this program you will be able to delve into aspects such as computer vision for the study of space and for content analysis, in the search for patterns and codes, in 3D image processing libraries or in autoencoders. 

The most comprehensive program on Computer Vision is waiting for you. Complete this program and access the future of the profession"

Module 1. Computer Vision

1.1. Human Perception 

1.1.1. Human Visual System 
1.1.2. Color 
1.1.3. Visible and Non-Visible Frequencies 

1.2. Summary of Computer Vision 

1.2.1. Principles 
1.2.2. Evolution 
1.2.3. The Importance of Computer Vision 

1.3. Digital Image Composition 

1.3.1. The Digital Image 
1.3.2. Types of Images 
1.3.3. Color Spaces 
1.3.4. RGB 
1.3.5. HSV and HSL 
1.3.6. CMY-CMYK 
1.3.7. YCbCr 
1.3.8. Indexed Image 

1.4. Image Acquisition Systems 

1.4.1. Operation of a Digital Camera 
1.4.2. The Correct Exposure for Each Situation 
1.4.3. Depth of Field 
1.4.4. Resolution 
1.4.5. Image Formats 
1.4.6. HDR Mode 
1.4.7. High Resolution Cameras 
1.4.8. High-Speed Cameras 

1.5. Optical Systems 

1.5.1. Optical Principles 
1.5.2. Conventional Lenses 
1.5.3. Telecentric Lenses 
1.5.4. Types of Autofocus Lenses 
1.5.5. Focal Length 
1.5.6. Depth of Field 
1.5.7. Optical Distortion 
1.5.8. Calibration of an Image 

1.6. Illumination Systems 

1.6.1. Importance of Illumination 
1.6.2. Frequency Response 
1.6.3. LED Illumination 
1.6.4. Outdoor Lighting 
1.6.5. Types of Lighting for Industrial Applications. Effects 

1.7. 3D Acquisition Systems 

1.7.1. Stereo Vision 
1.7.2. Triangulation 
1.7.3. Structured Light 
1.7.4. Time of Flight 
1.7.5. Lidar 

1.8. Multispectrum 

1.8.1. Multispectral Cameras 
1.8.2. Hyperspectral Cameras 

1.9. Non-Visible Near Spectrum 

1.9.1. IR Cameras 
1.9.2. UV Cameras 
1.9.3. Converting From Non-Visible to Visible by Illumination 

1.10. Other Band Spectrums 

1.10.1. X-Ray 
1.10.2. terahertz 

Module 2. Applications and State-of-the-Art 

2.1. Industrial Applications 

2.1.1. Machine Vision Libraries 
2.1.2. Compact Cameras 
2.1.3. PC-Based Systems 
2.1.4. Industrial Robotics 
2.1.5. Pick and Place 2D 
2.1.6. Bin Picking 
2.1.7. Quality Control 
2.1.8. Presence Absence of Components 
2.1.9. Dimensional Control 
2.1.10. Labeling Control 
2.1.11. Traceability 

2.2. Autonomous Vehicles 

2.2.1. Driver Assistance 
2.2.2. Autonomous Driving 

2.3. Computer Vision for Content Analysis 

2.3.1. Filtering by Content 
2.3.2. Visual Content Moderation 
2.3.3. Tracking Systems 
2.3.4. Brand and Logo Identification 
2.3.5. Video Labeling and Classification 
2.3.6. Scene Change Detection 
2.3.7. Text or Credits Extraction

2.4. Medical Application 

2.4.1. Disease Detection and Localization 
2.4.2. Cancer and X-Ray Analysis 
2.4.3. Advances in Computer Vision Due to Covid-19 
2.4.4. Assistance in the Operating Room 

2.5. Spatial Applications 

2.5.1. Satellite Image Analysis 
2.5.2. Computer Vision for the Study of Space 
2.5.3. Mission to Mars 

2.6. Commercial Applications 

2.6.1. Stock Control 
2.6.2. Video Surveillance, Home Security 
2.6.3. Parking Cameras 
2.6.4. Population Control Cameras 
2.6.5. Speed Cameras 

2.7. Vision Applied to Robotics 

2.7.1. Drones 
2.7.2. AGV 
2.7.3. Vision in Collaborative Robots 
2.7.4. The Eyes of the Robots

2.8. Augmented Reality 

2.8.1. Operation 
2.8.2. Devices 
2.8.3. Applications in the Industry 
2.8.4. Commercial Applications 

2.9. Cloud Computing 

2.9.1. Cloud Computing Platforms 
2.9.2. From Cloud Computing to Production 

2.10. Research and State-of-the-Art 

2.10.1. Commercial Applications 
2.10.2. What's Cooking? 
2.10.3. The Future of Computer Vision 

Module 3. Digital Image Processing 

3.1. Computer Vision Development Environment 

3.1.1. Computer Vision Libraries 
3.1.2. Programming Environment 
3.1.3. Visualization Tools 

3.2. Digital image Processing 

3.2.1. Pixel Relationships 
3.2.2. Image Operations 
3.2.3. Geometric Transformations 

3.3. Pixel Operations 

3.3.1. Histogram 
3.3.2. Histogram Transformations 
3.3.3. Operations on Color Images 

3.4. Logical and Arithmetic Operations 

3.4.1. Addition and Subtraction 
3.4.2. Product and Division 
3.4.3. And/Nand 
3.4.4. Or/Nor 
3.4.5. Xor/Xnor 

3.5. Filters 

3.5.1. Masks and Convolution 
3.5.2. Linear Filtering 
3.5.3. Non-Linear Filtering 
3.5.4. Fourier Analysis 

3.6. Morphological Operations

3.6.1. Erosion and Dilation 
3.6.2. Closing and Opening 
3.6.3. Top Hat and Black Hat 
3.6.4. Contour Detection 
3.6.5. Skeleton 
3.6.6. Hole Filling 
3.6.7. Convex Hull 

3.7. Image Analysis Tools 

3.7.1. Edge Detection 
3.7.2. Detection of Blobs 
3.7.3. Dimensional Control 
3.7.4. Color Inspection 

3.8. Object Segmentation 

3.8.1. Image Segmentation 
3.8.2. Classical Segmentation Techniques 
3.8.3. Real Applications 

3.9. Image Calibration 

3.9.1. Image Calibration 
3.9.2. Methods of Calibration 
3.9.3. Calibration Process in a 2D Camera/Robot System 

3.10. Image Processing in a Real Environment 

3.10.1. Problem Analysis 
3.10.2. Image Processing 
3.10.3. Feature Extraction 
3.10.4. Final Results 

Module 4. Advanced Digital Image Processing 

4.1. Optical Character Recognition (OCR) 

4.1.1. Image Pre-Processing 
4.1.2. Text Detection 
4.1.3. Text Recognition 

4.2. Code Reading 

4.2.1. 1D Codes 
4.2.2. 2D Codes 
4.2.3. Applications 

4.3. Pattern Search 

4.3.1. Pattern Search 
4.3.2. Patterns Based on Gray Level 
4.3.3. Patterns Based on Contours 
4.3.4. Patterns Based on Geometric Shapes 
4.3.5. Other Techniques 

4.4. Object Tracking with Conventional Vision 

4.4.1. Background Extraction 
4.4.2. Meanshift 
4.4.3. Camshift 
4.4.4. Optical Flow 

4.5. Facial Recognition 

4.5.1. Facial Landmark Detection 
4.5.2. Applications 
4.5.3. Facial Recognition 
4.5.4. Emotion Recognition 

4.6. Panoramic and Alignment 

4.6.1. Stitching 
4.6.2. Image Composition 
4.6.3. Photomontage 

4.7. High Dynamic Range (HDR) and Photometric Stereo 

4.7.1. Increasing the Dynamic Range 
4.7.2. Image Compositing for Contour Enhancement 
4.7.3. Techniques for the Use of Dynamic Applications 

4.8. Image Compression 

4.8.1. Image Compression 
4.8.2. Types of Compressors 
4.8.3. Image Compression Techniques 

4.9. Video Processing 

4.9.1. Image Sequences 
4.9.2. Video Formats and Codecs 
4.9.3. Reading a Video
4.9.4. Frame Processing 

4.10. Real Application of Image Processing 

4.10.1. Problem Analysis 
4.10.2. Image Processing 
4.10.3. Feature Extraction 
4.10.4. Final Results 

Module 5. 3D Image Processing 

5.1. 3D Imaging 

5.1.1. 3D Imaging 
5.1.2. 3D Image Processing Software and Visualizations 
5.1.3. Metrology Software 

5.2. Open 3D 

5.2.1. Library for 3D Data Processing 
5.2.2. Features 
5.2.3. Installation and Use 

5.3. The Data 

5.3.1. Depth Maps in 2D Image 
5.3.2. Pointclouds 
5.3.3. Normal 
5.3.4. Surfaces 

5.4. Visualization 

5.4.1. Data Visualization 
5.4.2. Controls 
5.4.3. Web Display 

5.5. Filters 

5.5.1. Distance Between Points, Eliminate Outliers 
5.5.2. High Pass Filter 
5.5.3. Downsampling 

5.6. Geometry and Feature Extraction 

5.6.1. Extraction of a Profile 
5.6.2. Depth Measurement 
5.6.3. Volume 
5.6.4. 3D Geometric Shapes 
5.6.5. Shots 
5.6.6. Projection of a Point 
5.6.7. Geometric Distances 
5.6.8. Kd Tree 
5.6.9. 3D Features 

5.7. Registration and Meshing 

5.7.1. Concatenation 
5.7.2. ICP 
5.7.3. Ransac 3D 

5.8. 3D Object Recognition 

5.8.1. Searching for an Object in the 3D Scene 
5.8.2. Segmentation. 
5.8.3. Bin Picking 

5.9. Surface Analysis 

5.9.1. Smoothing 
5.9.2. Orientable Surfaces 
5.9.3. Octree 

5.10. Triangulation 

5.10.1. From Mesh to Point Cloud 
5.10.2. Depth Map Triangulation 
5.10.3. Triangulation of Unordered Point Clouds 

Module 6. Deep Learning  

6.1. Artificial Intelligence 

6.1.1. Machine Learning 
6.1.2. Deep Learning 
6.1.3. The Explosion of Deep Learning Why Now? 

6.2. Neural Networks 

6.2.1. The Neural Network 
6.2.2. Uses of Neural Networks 
6.2.3. Linear Regression and Perceptron 
6.2.4. Forward Propagation 
6.2.5. Backpropagation 
6.2.6. Feature Vectors 

6.3. Loss Functions 

6.3.1. Loss Functions 
6.3.2. Types of Loss Functions 
6.3.3. Choice of Loss Functions 

6.4. Activation Functions 

6.4.1. Activation Function 
6.4.2. Linear Functions 
6.4.3. Non-Linear Functions 
6.4.4. Output vs. Hidden Layer Activation Functions 

6.5. Regularization and Normalization 

6.5.1. Regularization and Normalization 
6.5.2. Overfitting and Data Augmentation 
6.5.3. Regularization Methods: L1, L2 and Dropout 
6.5.4. Normalization Methods: Batch, Weight, Layer

6.6. Optimization 

6.6.1. Gradient Descent 
6.6.2. Stochastic Gradient Descent 
6.6.3. Mini Batch Gradient Descent 
6.6.4. Momentum 
6.6.5. Adam 

6.7. Hyperparameter Tuning and Weights 

6.7.1. Hyperparameters 
6.7.2. Batch Size vs. Learning Rate vs. Step Decay 
6.7.3. Weights 

6.8. Evaluation Metrics of a Neural Network 

6.8.1. Accuracy 
6.8.2. Dice Coefficient 
6.8.3. Sensitivity vs. Specificity/Recall vs. Precision 
6.8.4. ROC Curve (AUC) 
6.8.5. F1-Score 
6.8.6. Matrix Confusion 
6.8.7. Cross-Validation 

6.9. Frameworks and Hardware 

6.9.1. Tensor Flow 
6.9.2. Pytorch 
6.9.3. Caffe 
6.9.4. Keras 
6.9.5. Hardware for the Learning Phase  

6.10. Creation of a Neural Network-Training and Validation

6.10.1. Dataset 
6.10.2. Network Construction 
6.10.3. Training 
6.10.4. Visualization of Results 

Module 7. Convolutional Neural Networks and Image Classification 

7.1. Convolutional Neural Networks 

7.1.1. Introduction 
7.1.2. Convolution
7.1.3. CNN Building Blocks 

7.2. Types of CNN Layers 

7.2.1. Convolutional 
7.2.2. Activation 
7.2.3. Batch Normalization 
7.2.4. Polling 
7.2.5. Fully Connected 

7.3. Metrics 

7.3.1. Matrix Confusion 
7.3.2. Accuracy 
7.3.3. Precision 
7.3.4. Recall 
7.3.5. F1 Score 
7.3.6. ROC Curve 
7.3.7. AUC 

7.4. Main Architectures 

7.4.1. AlexNet 
7.4.2. VGG 
7.4.3. Resnet 
7.4.4. GoogleLeNet 

7.5. Image Classification 

7.5.1. Introduction 
7.5.2. Analysis of Data 
7.5.3. Data Preparation 
7.5.4. Model Training 
7.5.5. Model Validation 

7.6. Practical Considerations for CNN Training 

7.6.1. Optimizer Selection 
7.6.2. Learning Rate Scheduler 
7.6.3. Check Training Pipeline 
7.6.4. Training with Regularization 

7.7. Best Practices in Deep Learning 

7.7.1. Transfer Learning 
7.7.2. Fine Tuning 
7.7.3. Data Augmentation 

7.8. Statistical Data Evaluation 

7.8.1. Number of Datasets 
7.8.2. Number of Labels 
7.8.3. Number of Images 
7.8.4. Data Balancing 

7.9. Deployment 

7.9.1. Saving and Loading Models 
7.9.2. Onnx 
7.9.3. Inference 

7.10. Case Study: Image Classification 

7.10.1. Data Analysis and Preparation 
7.10.2. Testing the Training Pipeline 
7.10.3. Model Training 
7.10.4. Model Validation 

Module 8. Object Detection

8.1. Object Detection and Tracking 

8.1.1. Object Detection 
8.1.2. Case Uses 
8.1.3. Object Tracking 
8.1.4. Case Uses 
8.1.5. Occlusions, Rigid and Non-Rigid Poses 

8.2. Evaluation Metrics 

8.2.1. IOU - Intersection Over Union 
8.2.2. Confidence Score 
8.2.3. Recall 
8.2.4. Precision 
8.2.5. Recall–Precision Curve 
8.2.6. Mean Average Precision (mAP) 

8.3. Traditional Methods 

8.3.1. Sliding Window 
8.3.2. Viola Detector 
8.3.3. HOG 
8.3.4. Non-Maximal Suppresion (NMS) 

8.4. Datasets 

8.4.1. Pascal VC 
8.4.2. MS Coco 
8.4.3. ImageNet (2014) 
8.4.4. MOTA Challenge 

8.5. Two Shot Object Detector 

8.5.1. R-CNN 
8.5.2. Fast R-CNN 
8.5.3. Faster R-CNN 
8.5.4. Mask R-CNN 

8.6. Single Shot Object Detector  

8.6.1. SSD 
8.6.2. YOLO 
8.6.3. RetinaNet 
8.6.4. CenterNet 
8.6.5. EfficientDet 

8.7. Backbones 

8.7.1. VGG 
8.7.2. ResNet 
8.7.3. Mobilenet 
8.7.4. Shufflenet 
8.7.5. Darknet 

8.8. Object Tracking 

8.8.1. Classical Approaches 
8.8.2. Particulate Filters 
8.8.3. Kalman 
8.8.4. Sorttracker 
8.8.5. Deep Sort 

8.9. Deployment 

8.9.1. Computing Platform 
8.9.2. Choice of Backbone 
8.9.3. Choice of Framework 
8.9.4. Model Optimization 
8.9.5. Model Versioning 

8.10. Study: Detection and Tracking of Individuals  

8.10.1. Detection of People 
8.10.2. Monitoring of People 
8.10.3. Re-Identification 
8.10.4. Counting People in Crowds 

Module 9. Image Segmentation with Deep Learning 

9.1. Object Detection and Segmentation 

9.1.1. Semantic Segmentation 

9.1.1.1. Semantic Segmentation Use Cases 

9.1.2. Instantiated Segmentation 

9.1.2.1. Instantiated Segmentation Use Cases 

9.2. Evaluation Metrics 

9.2.1. Similarities with Other Methods 
9.2.2. Pixel Accuracy 
9.2.3. Dice Coefficient (F1 Score) 

9.3. Cost Functions 

9.3.1. Dice Loss 
9.3.2. Focal Loss 
9.3.3. Tversky Loss 
9.3.4. Other Functions 

9.4. Traditional Segmentation Methods 

9.4.1. Threshold Application with Otsu and Riddlen 
9.4.2. Self-Organized Maps 
9.4.3. GMM-EM Algorithm 

9.5. Semantic Segmentation Applying Deep Learning: FCN 

9.5.1. FCN 
9.5.2. Architecture 
9.5.3. FCN Applications 

9.6. Semantic Segmentation Applying Deep Learning: U-NET 

9.6.1. U-NET 
9.6.2. Architecture 
9.6.3. U-NET Application 

9.7. Semantic Segmentation Applying Deep Learning: Deep Lab 

9.7.1. Deep Lab 
9.7.2. Architecture 
9.7.3. Deep Lab Application 

9.8. Instantiated Segmentation Applying Deep Learning: Mask RCNN 

9.8.1. Mask RCNN 
9.8.2. Architecture 
9.8.3. Application of a Mask RCNN 

9.9. Video Segmentation 

9.9.1. STFCN 
9.9.2. Semantic Video CNNs 
9.9.3. Clockwork Convnets 
9.9.4. Low-Latency 

9.10. Point Cloud Segmentation 

9.10.1. The Point Cloud 
9.10.2. PointNet 
9.10.3. A-CNN 

Module 10. Advanced Image Segmentation and Advanced Computer Vision Techniques 

10.1. Database for General Segmentation Problems  

10.1.1. Pascal Context 
10.1.2. CelebAMask-HQ 
10.1.3. Cityscapes Dataset 
10.1.4. CCP Dataset 

10.2. Semantic segmentation in medicine 

10.2.1. Semantic segmentation in medicine 
10.2.2. Datasets for Medical Problems 
10.2.3. Practical Applications 

10.3. Annotation Tools 

10.3.1. Computer Vision Annotation Tool 
10.3.2. LabelMe 
10.3.3. Other Tools 

10.4. Segmentation Tools Using Different Frameworks 

10.4.1. Keras 
10.4.2. Tensorflow v2 
10.4.3. Pytorch 
10.4.4. Others 

10.5. Semantic Segmentation Project. The Data, Phase 1 

10.5.1. Problem Analysis 
10.5.2. Input Source for Data 
10.5.3. Data Analysis 
10.5.4. Data Preparation 

10.6. Semantic Segmentation Project. Training, Phase 2 

10.6.1. Algorithm Selection 
10.6.2. Training 
10.6.3. Assessment 

10.7. Semantic Segmentation Project. Results, Phase 3 

10.7.1. Fine Tuning 
10.7.2. Presentation of The Solution 
10.7.3. Conclusions 

10.8. Autoencoders 

10.8.1. Autoencoders 
10.8.2. Architecture of an Autoencoder 
10.8.3. Noise Removal Autoencoders 
10.8.4. Automatic Coloring Autoencoder 

10.9. Generative Adversarial Networks (GANs) 

10.9.1. Generative Adversarial Networks (GANs) 
10.9.2. DCGAN Architecture 
10.9.3. Conditional GAN Architecture 

10.10. Enhanced Generative Adversarial Networks 

10.10.1. Overview of the Problem 
10.10.2. WGAN 
10.10.3. LSGAN 
10.10.4. ACGAN

This Professional master’s degree has the most in-depth and up-to-date content in Computer Vision. Do not miss the opportunity and enroll now"