Sei sulla pagina 1di 2

AN IMPROVISED VERSION OF COLOR IMAGE CLASSIFICATION 2019-2020

USING UNSUPERVISED CLUSTERING TECHNIQUE

SYNOPSIS
Introduction:

Camera trapping collects images often result in low image quality and includes a lot of false
positives (images without animals), which must be detection before the post processing step.
This paper presents a two-channeled perceiving residual pyramid networks (TPRPN) for camera
trap images objection. Our TPRPN model attends to generating high-resolution and high-quality
results. In order to provide enough local information, we extract depth cue from the original
images and use two-channeled perceiving model as input to training our networks. Experimental
results on our dataset demonstrate that our method is superior to the existing object detection
methods.

OBJECTIVE:

To condense the mass data in such a manner that it can be easily apprehended. To facilitate
comparison. To pinpoint the most significant features of the data at a glance. In our project we
will capture the image of the Animal using camera and identify the type of animal.

Methodology:

To obtain (correct) predictions from deep neural networks we first need to preprocess our data.In
the context of deep learning and image classification, these preprocessing tasks normally
involve: Mean subtraction and Scaling by some factor.

OpenCV’s new deep neural network ( dnn ) module contains two functions that can be used for
preprocessing images and preparing them for classification via pre-trained deep learning models.

System Architecture:

Dept. Of CSE, Dr. TTIT, K.G.F 1


AN IMPROVISED VERSION OF COLOR IMAGE CLASSIFICATION 2019-2020
USING UNSUPERVISED CLUSTERING TECHNIQUE

FIGURE: SYSTEM ARCHITECTURE

OpenCV provides two functions to facilitate image preprocessing for deep learning
classification: cv2.dnn.blobFromImage and cv2.dnn.blobFromImages. These two functions
perform Mean subtraction,Scaling and optionally channel swapping . Both blob From
Image and blob From Images perform mean subtraction and scaling. We can also swap the Red
and Blue channels of the image depending on channel ordering. Nearly all state-of-the-art deep
learning models perform mean subtraction and scaling — the benefit here is that OpenCV makes
these preprocessing tasks dead simple.

Conclusion:

The system designed shown in the block diagram performs the detection and counting of the
Wild Animals. Here first the image is captured by using a camera and which is then converted to
a grey scale image to make it feasible for comparison with the existing data set values. The
existing systems like bar code scanners and manually counting of livestock is not beneficial as it
consumes a lot of time and the error margin becomes high so to overcome such hurdles we have
designed a real time system that performs such a task with efficiency and is cost effective.

…………………… ……………………
Signature of guide Signature of HOD
Mrs. Punitha F. Dr. Sreedhar Kumar S.

Dept. Of CSE, Dr. TTIT, K.G.F 2

Potrebbero piacerti anche