Scribd
Upload
57 views7 pages

Bird Project Design Format 2023

The document discusses a project to develop a bird species identification application using deep learning. It provides problem statement, block diagrams, use case diagram, data flow diagrams from different levels showing the workflow, activity diagram, sequence diagram, collaboration diagram, dataset description and algorithms used.

Uploaded by

Soumya Tole
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
57 views7 pages

Bird Project Design Format 2023

The document discusses a project to develop a bird species identification application using deep learning. It provides problem statement, block diagrams, use case diagram, data flow diagrams from different levels showing the workflow, activity diagram, sequence diagram, collaboration diagram, dataset description and algorithms used.

Uploaded by

Soumya Tole
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

“BIRD SPECIES IDENTIFICATION USING DEEP

LEARNING”

Design

Submitted by

Soumya S Tole

2KE21MC053

Project Guide

Mr Prasanna.B

Associate professor

Department of Master of Computer Applications

K.L.E. Institute of Technology


Hubballi - 580027
2022-23
BIRD SPECIES IDENTIFICATION USING DEEP
LEARNING

1 Problem statement
Nowadays we find a lot of birds in our day-to-day life and find it difficult to segregate its
kind, know its type, wonder where it is from and etc. There are many applications which
identify the bird through its voice and image. But still, ornithologists are finding it difficult to
get a quality application that provides necessary details for betterment in knowing better
details about a bird they could see.

2 Block diagram

3 Use case diagram


4. Data Flow Diagram
4.1 Data flow diagram level 0 for bird species identification

4.2 Detailed Data flow Diagram level 1 for bird species identification
4.3 End to End data flow diagram level 2 for bird species identification
5 Activity Diagram

6 Sequence Diagram
7 Collaboration diagram

8 Data set description


Data set used from Kaggle site which the total dataset consists of 15,882 images which
contain train test valid. The train images consist of 10,888 and the test images consists of
approximately 2000 images and valid also includes 2000 images. Here the aim of choosing
the dataset is to get the accuracy in high percentage. If the accuracy is high then we can get
the accurate result of the pre-processing images.

There are 100 classes in the dataset where each class consists minimum 100 to 150
images. Total we can get 15000 images of the bird it results to accurate and clear picture for
recognizing the bird species.
9 Algorithms working
The algorithm used is the convolutional neural network that is CNN Algorithm module which
consists of different layers they are pooling layer, convolutional layer, activation layer,
flattered layer, fully connected layer.

You might also like