This is my PPT on mini project on Image Classifier. It's was appreciated by my HOD of CSE of BBDU, Lucknow. It's easy and simple. I put some transitions in it too. So nobody has to think how to put transitions. I tried my best to make it simple for you all. Else you can put your own transiti...
This is my PPT on mini project on Image Classifier. It's was appreciated by my HOD of CSE of BBDU, Lucknow. It's easy and simple. I put some transitions in it too. So nobody has to think how to put transitions. I tried my best to make it simple for you all. Else you can put your own transitions in it, by simple downloading it.
PLEASE DO LIKE AND SHARE.
Thank You
Size: 921.55 KB
Language: en
Added: Oct 29, 2018
Slides: 23 pages
Slide Content
Image Classifier Project Presentation Presentation by: Faiz Ahmad Khan B. Tech (CSE) VII SEM Univ. Roll no.:1150432059 Class Roll no.:22
About Project This project was totally based on machine learning, i.e., supervised learning .The project was using CNN(Convolutional Neural Network). This project will be helpful in recognizing different images easily .It uses big data to make machine learn. Main objective of this project is to make the machine learn so that it can be used for training and education purpose. This future scope of this project can be useful in many ways .For ex, In Medical, etc.
Project Details in brief
About CNN (Convolutional Neural Network) CNN has wide applications in image and video recognition. CNNs, like neural networks, are made up of neurons with learnable weights and biases. Each neuron receives several inputs, takes a weighted sum over them, pass it through an activation function and responds with an output.
The whole network has a loss function and all the tips and tricks that we developed for neural networks still apply on CNNs.
About Supervised Learning Supervised learning, in the context of artificial intelligence (AI) and machine learning, is a type of system in which both input and desired output data are provided. Input and output data are labelled for classification to provide a learning basis for future data processing. Supervised machine learning systems provide the learning algorithms with known quantities to support future judgments.
Chatbots, self-driving cars, facial recognition programs, expert systems and robots are among the systems that may use either supervised or unsupervised learning . Supervised learning systems are mostly associated with retrieval-based AI but they may also be capable of using a generative learning model.
Project Work
About Project Name :- Image Classifier Platform:- Python with Tenserflow using CNN Date of presentation:- 24 th October, 2018 Guider :- Prof. Dr. Devendra Agarwal Sir, H.O.D. of CSE Location:- Babu Banarasi Das University, L.K.O ., 226028
System Requirements RAM -> 4gb(Minimum) 8gb(Maximum) HDD -> 500gb(Normal) -requires 20gb free space- O.S. -> Windows7/8//8.1/10, Linux, Mac OS
Tools & Technology Used Server Side :J SP Client Side :HTML , JavaScript, CSS Database :MYSQL Server Web Server :Apache Tomcat or Glassfish IDE : Netbeans
Purpose of project: Purpose of this project (Image Classifier) is that to learn how to make machine learn, i.e., by using supervised learning using CNN structure. This project helps in training and education fields. And also in many fields like Medical Sciences too. It uses big data to classify between images and the best part is that this can search image in offline mode too.
Synopsis of project
1. Coding Synopsis
Check.py : It checks the neural network with new input that the network has not seen before.
Structure.py : Defines the structure of the Convolutional Neural network
Flowers : it is where all the data or dataset used to train the neural network exists.
2. Output Synopse
Output :- The output is this.
Future Scope
About Future Scope of project The future scope of this project is that, when this software is ready. Then, it helps government in recognizing and in tracking people and things. AI helps in performing surgeries, reprogramming defects in human DNA, diagnosing medical conditions, automatic driving in all forms of vehicles.
The future image classification techniques helps in scanning every human and knowing the difference in everones personality traits. It can help in preventing cancer from increasing.