(este material tambien esta disponible en las clases de cada capitulo)

• 0.1-Programa del Curso [PDF]
• 0.1-Neural Networks and Deep Learning (Aggarwal, 2019) [Book]
• 0.1-Deep Learning (Goodfellow, 2016) [Book]
• 0.1-Computer Vision (Szeliski, 2010) [Book]
• 0.1-Multiple View Geometry in Computer Vision (Hartley, 2004) [Book]
• 0.1-Computer Vision for X-ray Testing (Mery, 2015) [Book]
• 1.1-Definiciones [PPT]
• 1.2-Historia [PPT]
• 1.2-Historia [PPT]
• 1.2-Vanishing points - perspective [Video]
• 1.2-Maquina de la perspectiva [Video]
• 1.2-Ejemplo 3D model de Vermer en SketchUp [3D Model]

• 2.1-Apuntes (ver capitulo 3) [Book]
• 2.1-Coordenadas homogeneas: puntos, lineas, planos [PPT]
• 2.1-Ejercicios puntos y lineas [Guia de Ejercicio]
• 2.1-Explicacion 68 landmarks [jpg]
• 2.1-Foto John Lennon [jpg]
• 2.2-Landmarks (x,y) de foto de John Lennon [matlab]
• 2.2-Landmarks x de foto de John Lennon [npy]
• 2.2-Landmarks y de foto de John Lennon [npy]

• 2.1-Transformaciones 2D-2D [PPT]
• 2.1-Ejemplo Transformaciones 2D [Matlab]
• 2.1-Transformaciones 3D-3D [PPT]
• 2.1-Transformaciones 3D-2D [PPT]
• 2.2-Ejemplo 3D de una piramide [Matlab]
• 2.2-Ejemplo perspectiva (GUI) [Matlab]
• 2.2--> Ejemplo perspectiva (fig file necesario para GUI) [Matlab]
• 2.2--> Ejemplo perspectiva (funcion necesaria para GUI) [Matlab]
• 2.2--> Ejemplo perspectiva (funcion necesaria para GUI) [Matlab]
• 2.2--> Ejemplo perspectiva (datos mesh para GUI) [Matlab]
• 2.2--> Ejemplo perspectiva (datos de perspectiva para GUI) [Matlab]

• 2.1-Ejercicios de transformaciones 2D y 3D [Guia de Ejercicio]

• 2.3-Homografias [PPT]
• 2.3-RANSAC [Matlab]
• 2.3-Homografias con RANSAC [Matlab]
• 2.3-Mosaicos [PPT]
• 2.3-SIFT [PPT]
• 2.3-Ejemplo DoG en SIFT [Matlab]
• 2.3-Ejemplo keypoints usand DoG [Matlab]
• 2.3-Ejemplo SIFT [Matlab]
• 2.3-Video de ejemplo [Video]

• 2.2-Reconstruccion 3D [PPT]
• 2.2-Ejemplo reconstruccion 3D [Matlab]
• 2.2-Calibracion (ver seccion 3.4) [Book]
• 2.2-Calibracion [PPT]
• 2.2-Calibracion [Matlab]
• 2.2-Ejemplo Calibracion [Matlab]
• 2.2-Ejemplo Calibracion [Matlab]
• 2.3-Calibracion Python [Python]
• 2.4-Geometria Epipolar [PPT]
• 2.4-Ejemplo geometria epipolar [Matlab]
• 2.4-Geometria Trifocal [Matlab]
• 2.4-Aplicaciones de multiples vistas [PPT]
• 2.4-Datos matrices de projeccion [Matlab]

• 2.3-Ejercicio homografia avanzada [Guia de Ejercicio]

• 2.5-Desarrollo de Proyecto 1 [Guia de Ejercicio]

• 2.5-Mosaicos en la practica (1) [PDF]
• 2.5-Mosaicos en la practica (2) [PDF]
• 2.5-Mosaicos en la practica (3) [PPT]
• 2.5-Mosaicos con Python [Code]
• 2.5-SIFT mosaic con Matlba (vlfeat toolbox) [Code]
• 2.5-From SIFT to Deep Learning [Nota Periodistica]
• 2.5-Creating Full View Panoramic Image Mosaics [Paper]
• 2.5-Cylindrical transform [Matlab]
• 2.5-Cylindrical transform [Diagram]

• 3.1-CNN [PPT]
• 3.1-Introduction to deep Learning from scratch [Blog]
• 3.1-Deep Learning from Scratch and Using Tensorflow in Python [Blog]
• 3.1-Ejemplo de reconocimiento eyes and nose [Code]
• 3.1-Eyes and nose dataset [Dataset]
• 3.1-Deep Learning and Reinforcement Learning Workflows (Matlab) [Blog]

• 2.5-Presentaciones Proyecto 1

• 3.1-Ejercicio Cats and Dogs [Code]
• 3.1-Dataset Cats and Dogs [Dataset]

• 3.1-Deep Face [PPT]
• 3.1-ArcFace [Paper]
• 3.1-Loss functions en ArcFace [Apuntes]

• 3.1-Ejercicio Face Recognition [Code]

• 3.1-Facial Analysis [PPT]
• 3.1-Face detection [Code]
• 3.1-Face detection [Paper]
• 3.1-Facial Analysis [Paper]
• 3.1-Building Face Recognition using FaceNet [Blog]
• 3.1-Reconocimiento de expresiones faciales [Code]
• 3.1-Deep Facial Expression Recognition: A Survey [Paper]
• 3.1-Estimacion de edad a partir de imagen facial [Code]
• 3.1-Extraccion de landmarks faciales [Code]
• 3.1-Face clustering [Paper]
• 3.1-Pose estimation [Code]
• 3.1-Pose estimation [Code]
• 3.1-Learning Social Relation Traits from Face Images [Paper]

• 3.1-Ejercicio de reconocimiento de atributos faciales [Code]

• 3.2-Detectores (presentacion de Daniel Saavedra) [PDF]
• 3.2-Object detection con Yolo [Code]
• 3.2-Omni-benchmarking object detection [Blog]
• 3.2-Real-Time Object Detection using SlimYOLOv3 [Blog]
• 3.3-[opcional] GAN [Video]
• 3.3-[opcional] How to make a pizza [Paper]
• 3.4-[opcional] Image Registration [Nota Periodistica]

• 3.5-Desarrollo de Proyecto 2 [Enunciado]

• 3.5-Desarrollo de Proyecto 2 [Enunciado]

• 4.1-Expositor: Alejandro Barros [Pagina personal]
• 4.1-La algoritmificacion de nuestra convivencia [Paper]
• 4.1-Entrevista a Ananny - El Mercurio [PDF]
• 4.1-Presentacion de Alejandro Barros [PDF]
• 4.1-Es posible acabar con los sesgos de los algoritmos? (Baeza-Yates, Peiro) [Paper]
• 4.1-Bias on the web (BaezaYaes) [Paper]

• 4.1-Motivacion: Etica en Reconocimientoo Facial [PPT]
• 4.1-What is Going On With Facial Recognition? (Tech Insider) [Video]
• 4.2-Tu rostro entrena herramientas de reconocimiento facial [Nota Periodistica]
• 4.1-Monitoring workers [Nota Periodistica]
• 4.1-The biggest lie tech people tell themselves [Nota Periodistica]
• 4.1-Rankings de personas (C. Gutierrez) > pag 38 [Paper]
• 4.1-Uso de reconocimiento de caras en China (The Economist) [Video]
• 4.1-Uso de reconocimiento de caras en China (BBC) [Video]
• 4.1-Chinese video surveillance network used by the Australian Government [Video]
• 4.1-China embraces facial recognition technology (France24) [Video]
• 4.1-Next-Level Surveillance: China Embraces Facial Recognition [Video]
• 4.1-ICE Used Facial Recognition to Mine State Driver License Databases - The New York Times [Nota Periodistica]
• 4.1-Ant-facial recognition tech at the Hong Kong protests was an art project [Nota Periodistica]
• 4.1-Hong Kong protesters use lasers to avoid facial recognition cameras and blind police (The Independent) []
• 4.1-You are in a Police Lineup, Right Now - The New York Times [Opinion]
• 4.1-Garbage In, Garbage Out by Claire Garvie| Face Recognition on Flawed Data [Paper]
• 4.1-Facial Recognition - Art or Science? [Paper]
• 4.1-Prohibicion en San Francisco de reconocimiento facial [Nota Periodistica]
• 4.1-Colegio Sueco multado por usar reconocimiento facial [Nota Periodistica]
• 4.2-Camaras en el Instituto Nacional [Nota Periodistica]
• 4.2-Ingenieros UC desarrollan sistema automatizado para pasar lista en clases [Nota Periodistica]
• 4.2-Amazon Pitches Shady Facial Recognition Laws [Nota Periodistica]
• 4.2-But what if Rekognition gets it wrong? [Nota Periodistica]

• 4.1-Deep Nude [Nota Periodistica]
• 4.1-GDPR [Nota Periodistica]
• 4.1-The Delicate Ethics of Using Facial Recognition in Schools [Nota Periodistica]
• 4.1-We cannot trust AI systems built on deep learning alone [Nota Periodistica]
• 4.1-It is not too late to get biometrics right [Nota Periodistica]
• 4.1-Understanding algorithmic decision [Paper]
• 4.1-The Implications of Batch Normalization Patent [Blog]
• 4.1-A Worrying Analysis of Recent Neural Recommendation Approaches [Paper]
• 4.1-How machine learning in policing could fuel racial discrimination [Nota Periodistica]
• 4.2-Machine learning 'causing science crisis' [Nota Periodistica]
• 4.2-Fake news [Video]
• 4.2-Consejo para la transparencia [Nota Periodistica]
• 4.2-Why a Right to Explanation of Automated Decision-Making [Paper]
• 4.2-Algoritmos vs. Delicuencia [Nota Periodistica]
• 4.2-Aplicaciones y datos personales [Nota Periodistica]
• 4.2-Presentacion de Pablo Viollier [Pagina personal]
• 4.2-El cuerpo como dato (derechosdigitales.org) [Ensayo]
• 4.2-La biometria en Chile y sus riesgos [Paper]
• 4.2-U.S. House of Representatives [Nota Periodistica]
• 4.2-Politica de Amazon [Nota Periodistica]
• 4.2-How to Make A.I. That is Good for People [Nota Periodistica]
• 4.2-Controversia de Rekognition de Amazon [Nota Periodistica]
• 4.2-Reconocimiento Facial: es bueno o malo? (D.Mery) [Opinion]
• 4.2-Face Analysis: State of the Art and Ethical Challenges (D. Mery) [Paper]
• 4.2-Emociones desde una selfie [Nota Periodistica]
• 4.2-Cuanto valen tus datos digitales? [Nota Periodistica]
• 4.2-El reconocimiento facial debe postergarse [Nota Periodistica]
• 4.2-La tecnologia de reconocimiento facial de Amazon puede ser racista? [Nota Periodistica]
• 4.2-How to Thwart Facial Recognition [Nota Periodistica]
• 4.2-Face Recognition Accuracy Relative to Race [Paper]
• 4.2-Live facial recognition surveillance 'must stop' - BBC News [Nota Periodistica]
• 4.2-People Councils for Ethical Machine Learning [Paper]
• 4.2-Declarado improcedente el cese de un camarero que fue grabado robando [Nota Periodistica]
• 4.2-Global Hotel Recognition Dataset [Paper]
• 4.2-Is the United States prepared for the robotic revolution? [Nota Periodistica]
• 4.2-A new clothing line confuses automated license plate readers [Nota Periodistica]
• 4.2-The Danger of Over-Valuing Machine Learning [Nota Periodistica]
• 4.2-The Economist: Deepfake [Nota Periodistica]
• 4.2-Real-time object detection towards high power efficiency [Paper]
• 4.3-YouTube ayudo al surgimiento de la derecha y la radicalizacion en Brasil [Nota Periodistica]
• 4.2-Facial Recognition System for Getting Drunk More Efficiently Is Coming [Nota Periodistica]
• 4.2-Where might facial recognition be able to reduce wait times? [Nota Periodistica]
• 4.2-Un experto en inteligencia artificial quiere detener a los robots asesinos [Nota Periodistica]
• 4.2-Privacy and freedom of expression in the age of Artificial Intelligence [Nota Periodistica]
• 4.2-Data Anonymization - History and Key Ideas [Blog]
• 4.2-Explainable AI: The Next Frontier in Human-Machine Harmony [Blog]
• 4.2-Regulacion IARP [Link]
• 4.2-Attendance system [Link]
• 4.2-The Language of Congress [Link]
• 4.2-How Photos of Your Kids Are Powering Surveillance Technology - The New York Times [Nota Periodistica]
• 4.2-Appen Announces Crowd Code of Ethics to Build Better AI [Link]
• 4.2-You Got a Brain Scan at the Hospital. Someday a Computer May Use It to Identify You [Nota Periodistica]

• 3.5-Presentaciones Proyecto 2

Updated on 28-Oct-2019 at 15:43 by Domingo Mery