1 / 13

Major Project Review 2

Dos Bros Fresh Mexican Grill is a fast-casual restaurant in Evanston, IL, dedicated to serving fresh, made-to-order Mexican favorites. Their menu includes tacos, burritos, bowls, quesadillas, salads, and nachos, with customization options to accommodate vegan, vegetarian, and gluten-free diets.

dosbros
Télécharger la présentation

Major Project Review 2

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Department of Computer Science and Engineering Face Detection and Recognition in Organic Video : A Comparative Study for Sports Celebrities Database Presented By : Mohammed Ibrahim Khan Roll no: 160920733037 Syed Mohammed Akber Hussaini Roll no: 160920733051 Syed Mohammed Roll no: 160920733058 Under the Guidance of : Mr. Shaik Zubair Professor of CSE Department

  2. Agenda • Introduction • Aim and Objectives • Literature Review • Existing System • Proposed System • System Design

  3. Introduction to Face Detection and Recognition Software • Enhanced Security : • Accurate identification for access control. • Critical for surveillance and secure facilities. • Optimized User Experience : • Seamless interactions through facial authentication. • Personalized user experiences. • Digital Transformation : • Drives smart technology advancements. • Facilitates automation and intelligent systems. • Efficient Access Control : • Streamlines entry and authentication processes. • Reliable alternative to traditional methods. • Versatility in Applications : • Applicable across diverse industries. • Fosters innovation in digital platforms.

  4. Aim and Objectives Aim : To develop a software system that can detect and recognize faces in organic videos. Objectives : • Evaluate the performance of face detection algorithms (Haar Cascade Classifier and MMOD). • Assess the effectiveness of face recognition models (LSBH and CNN-based Pruned ResNet). • Compare combinations of face detection and recognition methods for organic video processing. • Analyze the impact of challenging scenarios on algorithm performance. • Discuss quantitative results for organic video content and celebrity face images.

  5. Literature Review

  6. Existing System System Architecture : SVM-based modules for face detection and recognition in organic videos (Pre-CNN Era) Modules : Face Detection module & Face Recognition Module Working of SVMs in Face Detection : • Training Data: Labeled dataset with positive and negative samples. • Features: Extraction of relevant features (e.g., Haar-like features). • Classification: SVMs classify image regions as containing faces or not. • Cascading: Integration into cascaded classifiers for efficient rejection of non-face regions. For face recognition : Extracting Facial features -> Training based on patterns of various individuals -> Testing Challenges : Limited adaptability to diverse organic video content, and large datasets

  7. Proposed System System Architecture : CNN-based Face Detection and Recognition Modules : Face Detection module & Face Recognition Module Face Detection Techniques : • Haar Cascade Classifier: A conventional face detection algorithm used for detecting frontal faces. • MMOD (Max-Margin Object Detection): A CNN designed for non-frontal face views Face Recognition Techniques : • LBPH (Local Binary Pattern Histogram): An ML-based face recognition algorithm used for recognizing faces based on local binary patterns. • CNN-based Pruned ResNet: A pruned version of ResNet-34, implemented for deep learning-based face recognition Advantages : Can handle diverse organic video content, and large datasets with accuracy

  8. System Design • UseCaseDiagram:FaceDetection&RecognitioninOrganic Video

  9. Activity Diagram:FaceDetection&RecognitioninOrganicVideo

  10. Sequence Diagram:FaceDetection&RecognitioninOrganicVideo

  11. Component Diagram:FaceDetection&RecognitioninOrganic Video

  12. Deployment Diagram:FaceDetection&RecognitioninOrganicVideo

More Related