1. INDUSTRY ORIENTED MINI PROJECT PRESENTATION
ON
AI based Detection to find the different objects with in the part of image
BATCH NO : A - 13
UNDER THE ESTEEMED GUIDANCE OF : MR. G RAVI,
ASSISTANT PROFESSOR.
NAME OF PROJECT COORDINATOR:
PROJECT BATCH STUDENTS NAMES &
ROLL NUMBERS
20BK5A0416 – B. JAYENDRANATH
20BK5A0404 – A. ISAAC PAUL
20BK5A0413 – B. PRATHYUSHA
2. ABSTRACT
In this project we will see deeper and look at various algorithms that can be used for object
detection. We will start with the algorithms belonging to RCNN family, i.e. RCNN, Fast
RCNN and Faster RCNN. In the upcoming article of this series, we will cover more
advanced algorithms like YOLO, SSD, etc. Main use of this project is to detect the objects
at any type and covert the object into speech. We can detect with in seconds using YOLO
with RCNN. using this we can detect images, create images. Yolo gives better output and
taking less speed than others.
3. INTRODUCTION
• The algorithm applies a neural network to an entire image. The network divides the
image into an S x S grid and comes up with bounding boxes, which are boxes drawn
around images and predicted probabilities for each of these regions.
• The method used to come up with these probabilities is logistic regression. The bounding
boxes are weighted by the associated probabilities. For class prediction, independent
logistic classifiers are used.
• In this article, demonstrate how to implement the YOLO algorithm with a pre trained
model.
• First, we would need to install DarkNet. it is a neural network framework that is open
source.
4. EXISTING SYSTEM
• Edge detection.
• Morphological filters.
• Svm classification.
DISADVANTAGES:
• Not a real time application.
• Information of objects is very less
5. PROPOSED SYSTEM
• Caffe model data set(Darknet)
• Deep learning classification
• Blob detection
ADVANTAGES:
• Maximum accuracy in classification
• Real time achievement
• Machine based prediction
APPLICATIONS:
• Commercial applications
• Forensic lab
• Face recognition
8. RESULTS AND DISCUSSION
The important discussion in our project is detect objects using yolo with rcnn. So,
take yolo and detect every object with in less time and get more accuracy. These
are used for the face recognition
9. CONCLUSION AND FUTURE SCOPE
We introduce YOLO, a unified model for object detection. Our model is simple
to construct and can be trained directly on full images. Unlike classifier-based
approaches, YOLO is trained on a loss function that directly corresponds to
detection performance and the entire model is trained jointly. Fast YOLO is the
fastest general-purpose object detector in the literature and YOLO pushes the
state-of-the-art in real-time object detection. YOLO also generalizes well to
new domains making it ideal for applications that rely on fast, robust object
detection. then detected image is converted into text,after that text to speech
conversion occure.