IMAGE PROCESSING FACIAL EXPRESSION RECOGNITION

1 IMAGE PROCESSING FACIAL EXPRESSION RECOGNITION Report submitted for the partial fulfillment of the requirements for the degree of Bachelor of Technology in Information Technology Submitted by ANGANA MITRA University Roll No. 11700214011 Registration No. 141170110106 SOUVIK CHOUDHURY University Roll No. 11700214069 Registration No. - 141170110164 SUSMITA MOITRA University Roll No. 11700214080 Registration No. 141170110175 Under the Guidance of Mr. AMIT KHAN Assistant Professor, Department of Information Technology RCC Institute of Information Technology RCC Institute of Information Technology Acknowledgement We would like to express our sincere gratitude to Mr.

2 Amit Khan, Assistant Professor of the department of Information Technology, whose role as project guide was invaluable for the project. We are extremely thankful for the keen interest he took in advising us, for the books and reference materials provided for the moral support extended to us. Last but not the least we convey our gratitude to all the teachers for providing us the technical skill that will always remain as our asset and to all non-teaching staff for the gracious hospitality they offered us.

3 Place: RCCIIT, Kolkata Date: 14th May, 2018 ANGANA MITRA SOUVIK CHOUDHURY SUSMITA MOITRA Department of Information Technology RCCIIT, Beliaghata, Kolkata 700 015, West Bengal, India Approval This is to certify that the project report entitled IMAGE PROCESSING ( FACIAL EXPRESSION RECOGNITION ) prepare under my supervision by ANGANA MITRA (11700214011), SOUVIK CHOUDHURY (11700214069) & SUSMITA MOITRA (11700214080) be accepted in partial fulfillment for the degree of Bachelor of Technology in Information Technology.

4 It is to be understood that by this approval, the undersigned does not necessarily endorse or approve any statement made, opinion expressed or conclusion drawn thereof, but approves the report only for the purpose for which it has been submitted. Mr. Amit Khan Assistant Professor, Department of Information Technology, RCCIIT, Kolkata Dr.

5 Abhijit Das ABSTRACT These Human FACIAL expressions convey a lot of information visually rather than articulately. FACIAL EXPRESSION RECOGNITION plays a crucial role in the area of human-machine interaction. Automatic FACIAL EXPRESSION RECOGNITION system has many applications including, but not limited to, human behavior understanding, detection of mental disorders, and synthetic human expressions. RECOGNITION of FACIAL EXPRESSION by computer with high RECOGNITION rate is still a challenging task. Two popular methods utilized mostly in the literature for the automatic FER systems are based on geometry and appearance.

6 FACIAL EXPRESSION RECOGNITION usually performed in four-stages consisting of pre- PROCESSING , face detection, feature extraction, and EXPRESSION classification. In this project we applied various deep learning methods (convolutional neural networks) to identify the key seven human emotions: anger, disgust, fear, happiness, sadness, surprise and neutrality. Table Of Contents Sl No. Topics Page No. 1. Introduction 1 2. Motivation 2 3. Problem Definition 3-4 4. Literature Study 5-11 5. Software Requirement 12 6. Planning 13 7. Design 14-17 8.

7 Algorithm 18 9. Implementation Details 19-30 10. Implementation Of Problem 31-37 11. Result 38-42 12. Conclusion 43 13. Future Scope 44 14. Reference 45-46 15. Appendix 47-61 Index Of Images Sl No. Topics Pages 1. Basic Human Emotion 1 Monaliza 2 Deaf & Dumb 2 3. Problem Formulation 3 Pre- PROCESSING 5 Face Registration 6 FACIAL Feature Extraction 6 Emotion Classification 6 Neural Network 7 Gabor Filter 8 FER2013 Images 19 FER2013 Sample 19 Python Alternative To Matlab 22 Haar Features 24 Adaboost 25 Cascade Workflow 26 Artificial Neural Network 28 Deep Convolution Neural Network Architecture 29 Convolution Neural Network Layers 30 Overview Of FER2013 Database 31 Training & Validation Data Distribution 31 FER CNN Architecture 32 Convolutional & Maxpooling Of

8 Neural Network 32 CNN Forward & Backward Propagation 33 Final Model CNN 34 Architecture Prediction Of Example Faces From Database 34-35 Confusion Matrix 36 Correct Prediction On 2nd & 3rd Highest Probable Emotion 36 CNN Feature Maps After 2nd Layer Of Maxpooling 37 CNN Feature Maps After 3rd Layer Of Maxpooling 37 Pixel Representation Of Database Images 37 Input Sample 1 40 Greyscale Sample 1 40 48*48 Greyscale Sample 1 40 Input Sample 2 41 Greyscale Sample 2 41 48*48 Greyscale Sample 2 41 Input Sample 3 42 Greyscale Sample 3 42 48*48 Greyscale Sample 3 42 Index Of Tables Sl.

9 No. Topics Pages 1. Accuracy of various database 10 2. Accuracy of various approaches are stated as follows 10-11 1. INTRODUCTION : 2018 is the year when machines learn to grasp human emotions --Andrew Moore, the dean of computer science at Carnegie Mellon. With the advent of modern technology our desires went high and it binds no bounds. In the present era a huge research work is going on in the field of digital IMAGE and IMAGE PROCESSING . The way of progression has been exponential and it is ever increasing.

10 IMAGE PROCESSING is a vast area of research in present day world and its applications are very widespread. IMAGE PROCESSING is the field of signal PROCESSING where both the input and output signals are images. One of the most important application of IMAGE PROCESSING is FACIAL EXPRESSION RECOGNITION . Our emotion is revealed by the expressions in our face. FACIAL Expressions plays an important role in interpersonal communication. FACIAL EXPRESSION is a non verbal scientific gesture which gets expressed in our face as per our emotions.