Learn about the most advanced computer vision techniques thanks to this Postgraduate diploma, which prepares you to successfully face all future challenges in the field of machine vision"

Computer vision is a complex and expanding field that is constantly adding new applications and utilities. Therefore, in order to get the most out of computer vision tools, it is important to master the most advanced and innovative techniques in this area. Accordingly, this Postgraduate diploma in Advanced Web-Based Computer Vision Techniques responds to this challenge, providing the professional with the most recent procedural and technological advances in this field.

In this program, therefore, computer scientists will be able to study aspects such as 2D image depth maps, depth measurement, 3D object recognition, semantic segmentation in medicine or point cloud segmentation, among many others, in depth. In this way, the engineer will have been able to access numerous new and high-level contents in this area.

And this will be achieved thanks to a specialized and very experienced teaching staff that knows all the keys to the discipline, in addition to the large number of multimedia resources available in this program, such as interactive summaries, practical exercises, master classes or videos of techniques and procedures.

Learn about new computer vision procedures and incorporate them into your work immediately with this educational program" 

This Postgraduate diploma in Advanced Web-Based Computer Vision Techniques contains the most complete and up-to-date program on the market. The most important features include:

• 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 the self-assessment process can be carried out 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

Develop great computer vision projects thanks to everything you will learn in this Postgraduate diploma"   

The program’s teaching staff includes professionals from sector who contribute their work experience to this 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. For this purpose, the student will be assisted by an innovative interactive video system created by renowned and experienced experts.

Your mastery of computer vision will give you access to numerous career opportunities in the best technology companies in the world"

You are looking for a program that will set you apart professionally and this is the perfect one for you, as it will allow you to become a computer vision specialist"

The contents of this Postgraduate diploma in Advanced Web-Based Computer Vision Techniques have been prepared by leading experts in this field, and have been structured into 3 specialized modules subdivided into 10 units each. Therefore, throughout the program, the computer scientist will be able to delve into issues such as 3D image processing software, the library for 3D data processing or semantic segmentation applying deep learning, among many others.

You won't find a more cutting-edge syllabus on advanced computer-processed vision techniques"

Module 1. 3D Image Processing 

1.1. 3D Imaging 

1.1.1. 3D Imaging 
1.1.2. 3D Image Processing Software and Visualizations 
1.1.3. Metrology Software 

1.2. Open 3D 

1.2.1. Library for 3D Data Processing 
1.2.2. Features 
1.2.3. Installation and Use 

1.3. The Data 

1.3.1. Depth Maps in 2D Image 
1.3.2. Point Clouds 
1.3.3. Normal 
1.3.4. Surfaces 

1.4. Visualization 

1.4.1. Data Visualization 
1.4.2. Controls 
1.4.3. Web Display 

1.5. Filters 

1.5.1. Distance Between Points, Eliminate Outliers 
1.5.2. High Pass Filter 
1.5.3. Downsampling 

1.6. Geometry and Feature Extraction 

1.6.1. Profile Extraction 
1.6.2. Depth Measurement 
1.6.3. Volume 
1.6.4. 3D Geometric Shapes 
1.6.5. Shots 
1.6.6. Projection of a Point 
1.6.7. Geometric Distances 
1.6.8. Kd Tree 
1.6.9. 3D Features 

1.7. Registration and Meshing 

1.7.1. Concatenation 
1.7.2. ICP 
1.7.3. Ransac 3D 

1.8. 3D Object Recognition 

1.8.1. Searching for an Object in the 3D Scene 
1.8.2. Segmentation. 
1.8.3. Bin Picking 

1.9. Surface Analysis 

1.9.1. Smoothing 
1.9.2. Orientable Surfaces 
1.9.3. Octree 

1.10. Triangulation 

1.10.1. From Mesh to Point Cloud 
1.10.2. Depth Map Triangulation 
1.10.3. Triangulation of Unordered Point Clouds 

Module 2. Image Segmentation with Deep Learning 

2.1. Object Detection and Segmentation 

2.1.1. Semantic Segmentation 

2.1.1.1. Semantic Segmentation Use Cases 

2.1.2. Instantiated Segmentation 

2.1.2.1. Instantiated Segmentation Use Cases 

2.2. Evaluation Metrics 

2.2.1. Similarities with Other Methods 
2.2.2. Pixel Accuracy 
2.2.3. Dice Coefficient (F1 Score) 

2.3. Cost Functions 

2.3.1. Dice Loss 
2.3.2. Focal Loss 
2.3.3. Tversky Loss 
2.3.4. Other Functions 

2.4. Traditional Segmentation Methods 

2.4.1. Threshold Application with Otsu and Riddlen 
2.4.2. Self-Organized Maps 
2.4.3. GMM-EM Algorithm 

2.5. Semantic Segmentation Applying Deep Learning: FCN 

2.5.1. FCN 
2.5.2. Architecture 
2.5.3. FCN Applications 

2.6. Semantic Segmentation Applying Deep Learning: U-NET 

2.6.1. U-NET 
2.6.2. Architecture 
2.6.3. U-NET Application 

2.7. Semantic Segmentation Applying Deep Learning: Deep Lab 

2.7.1. Deep Lab 
2.7.2. Architecture 
2.7.3. Deep Lab Application 

2.8. Instantiated Segmentation Applying Deep Learning: Mask RCNN 

2.8.1. Mask RCNN 
2.8.2. Architecture 
2.8.3. Application of a RCNN Mask  

2.9. Video Segmentation 

2.9.1. STFCN 
2.9.2. Semantic Video CNNs 
2.9.3. Clockwork Convnets 
2.9.4. Low-Latency 

2.10. Point Cloud Segmentation 

2.10.1. The Point Cloud 
2.10.2. PointNet 
2.10.3. A-CNN 

Module 3. Advanced Image Segmentation  and Advanced Computer Vision Techniques 

3.1. Database for General Segmentation Problems  

3.1.1. Pascal Context 
3.1.2. CelebAMask-HQ 
3.1.3. Cityscapes Dataset 
3.1.4. CCP Dataset 

3.2. Semantic Segmentation in Medicine 

3.2.1. Semantic Segmentation in Medicine 
3.2.2. Datasets for Medical Problems 
3.2.3. Practical Applications 

3.3. Annotation Tools 

3.3.1. Computer Vision Annotation Tool 
3.3.2. LabelMe 
3.3.3. Other Tools 

3.4. Segmentation Tools Using Different Frameworks 

3.4.1. Keras 
3.4.2. Tensorflow v2 
3.4.3. Pytorch 
3.4.4. Others 

3.5. Semantic Segmentation Project. The Data, Phase 1 

3.5.1. Problem Analysis 
3.5.2. Input Source for Data 
3.5.3. Data Analysis 
3.5.4. Data Preparation 

3.6. Semantic Segmentation Project. Training, Phase 2 

3.6.1. Algorithm Selection 
3.6.2. Training 
3.6.3. Assessment 

3.7. Semantic Segmentation Project. Results, Phase 3 

3.7.1. Fine Tuning 
3.7.2. Presentation of The Solution 
3.7.3. Conclusions a

3.8. Autoencoders 

3.8.1.  Autoencoders 
3.8.2. Architecture of an Autoencoder 
3.8.3. Noise Removal Autoencoders 
3.8.4. Automatic Coloring Autoencoder 

3.9. Generative Adversarial Networks (GANs) 

3.9.1. Generative Adversarial Networks (GANs) 
3.9.2. DCGAN Architecture 
3.9.3. Conditional GAN Architecture 

3.10. Enhanced Generative Adversarial Networks 

3.10.1. Overview of the Problem 
3.10.2. WGAN 
3.10.3. LSGAN 
3.10.4. ACGAN

The most complete and up-to-date computer vision syllabus on the market is here. Do not miss this great opportunity"