Age and Gender Classification using Convolutional Neural Networks

Slides:

Advertisements

Similar presentations

Face Recognition: A Convolutional Neural Network Approach

Advertisements

ImageNet Classification with Deep Convolutional Neural Networks

Example: ZIP Code Recognition Classification of handwritten numerals.

AN ANALYSIS OF SINGLE- LAYER NETWORKS IN UNSUPERVISED FEATURE LEARNING [1] Yani Chen 10/14/

Spatial Pyramid Pooling in Deep Convolutional

MACHINE LEARNING AND ARTIFICIAL NEURAL NETWORKS FOR FACE VERIFICATION

Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.

Convolutional Neural Networks for Image Processing with Applications in Mobile Robotics By, Sruthi Moola.

Presented by: Kamakhaya Argulewar Guided by: Prof. Shweta V. Jain

Hurieh Khalajzadeh Mohammad Mansouri Mohammad Teshnehlab

An Information Fusion Approach for Multiview Feature Tracking Esra Ataer-Cansizoglu and Margrit Betke ) Image and.

Dr. Z. R. Ghassabi Spring 2015 Deep learning for Human action Recognition 1.

Handwritten Hindi Numerals Recognition Kritika Singh Akarshan Sarkar Mentor- Prof. Amitabha Mukerjee.

Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.

Mentor Prof. Amitabha Mukerjee Deepak Pathak Kaustubh Tapi 10346

Convolutional Neural Network

Philipp Gysel ECE Department University of California, Davis

Lecture 4b Data augmentation for CNN training

Facial Smile Detection Based on Deep Learning Features Authors: Kaihao Zhang, Yongzhen Huang, Hong Wu and Liang Wang Center for Research on Intelligent.

Big data classification using neural network

Convolutional Neural Network

Deeply learned face representations are sparse, selective, and robust

Machine Learning for Big Data

Data Mining, Neural Network and Genetic Programming

Computer Science and Engineering, Seoul National University

DeepCount Mark Lenson.

Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek

A Pool of Deep Models for Event Recognition

Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay.

Can Computer Algorithms Guess Your Age and Gender?

Journal of Vision. 2017;17(4):9. doi: / Figure Legend:

Combining CNN with RNN for scene labeling (segmentation)

Ajita Rattani and Reza Derakhshani,

Inception and Residual Architecture in Deep Convolutional Networks

Hybrid Features based Gender Classification

Lecture 5 Smaller Network: CNN

Final Year Project Presentation --- Magic Paint Face

Mean Euclidean Distance Error (mm)

CS 698 | Current Topics in Data Science

CS6890 Deep Learning Weizhen Cai

Machine Learning: The Connectionist

Dynamic Routing Using Inter Capsule Routing Protocol Between Capsules

State-of-the-art face recognition systems

A Convolutional Neural Network Cascade For Face Detection

Layer-wise Performance Bottleneck Analysis of Deep Neural Networks

Bird-species Recognition Using Convolutional Neural Network

Introduction to Neural Networks

Counting in Dense Crowds using Deep Learning

Recurrent Neural Networks

Face Recognition with Neural Networks

network of simple neuron-like computing elements

Optimization for Fully Connected Neural Network for FPGA application

Lecture: Deep Convolutional Neural Networks

YOLO-LITE: A Real-Time Object Detection Web Implementation

Visualizing and Understanding Convolutional Networks

Analysis of Trained CNN (Receptive Field & Weights of Network)

RCNN, Fast-RCNN, Faster-RCNN

Outline A. M. Martinez and A. C. Kak, “PCA versus LDA,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp , 2001.

Deep Learning Some slides are from Prof. Andrew Ng of Stanford.

Earthen Mounds Recognition Using LiDAR Images

Face Recognition: A Convolutional Neural Network Approach

Department of Computer Science Ben-Gurion University of the Negev

Image Processing and Multi-domain Translation

CS295: Modern Systems: Application Case Study Neural Network Accelerator Sang-Woo Jun Spring 2019 Many slides adapted from Hyoukjun Kwon‘s Gatech “Designing.

End-to-End Facial Alignment and Recognition

CRCV REU 2019 Kara Schatz.

YOLO-based Object Detection on ARM Mali GPU

Sign Language Recognition With Unsupervised Feature Learning

Presented By: Firas Gerges (fg92)

Shengcong Chen, Changxing Ding, Minfeng Liu 2018

Presentation transcript:

Age and Gender Classification using Convolutional Neural Networks Gil Levi and Tal Hassner 2018 REU June 15, 2018 Rachel Huang

Goal Create a simple convolutional neural net architecture for gender classification and age estimation that can be used on “real-world” images Emphasize simple and “real-world”

Data set: Adience Collected from Flikr Around 26,000 images 2,284 subjects G. Levi and T. Hassner Mention the strange distribution of age

Image preprocessing Rescaled to 256x256 pixels Cropped to 227x227 pixels 1) Center cropping 2) Over-sampling -> yielded higher accuracy

Fully Connected Neural Network Convolutional Neural Network Fully connected: have a large number of parameters, expensive in memory and computation. Mention weights, bias Conv: specialized, extracts features https://medium.com/@curiousily/tensorflow-for-hackers-part-iv-neural-network-from-scratch-1a4f504dfa8 http://www.mdpi.com/2078-2489/7/4/61

Network Architecture 3 convolutional layers: 1) 96 filters of 3x7x7 pixels 2) 256 filters of 96x5x5 pixels 3) 384 filters of 256x3x3 pixels 2 fully connected layers —————————————————— 5 layers G. Levi and T. Hassner There’s actually a third fully connected layer that maps to final classes This is considered a “shallow network”

Results (this paper) Results (2017 paper) G. Levi and T. Hassner G. Antipov, M. Baccouche, S.-A. Berrani, and J.-L. Dugelay 2017 paper was pretrained on facial recognition, tested on several different neural networks, used a different method of grouping the ages called Label Distribution and Age Encoding (LDAE)

Dr. Wang Dr. Chen 97% Male 88% Female 45% 25-32 years old Dr. Wang original 53% Female 62% 25-32 years old 17% 15-20 years old Used GoogleNet implementation in tensorflow

Conclusion CNN improves performance of age and gender classification Using a more elaborate system could significantly increase accuracy Good baseline for future training and testing

Questions?

References G. Levi and T. Hassner, “Age and gender classification using convolutional neural networks,” 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2015. G. Antipov, M. Baccouche, S.-A. Berrani, and J.-L. Dugelay, “Effective training of convolutional neural networks for face-based gender and age prediction,” Pattern Recognition, vol. 72, pp. 15–26, 2017.