Abstract
Machine learning based approach for
the detection and classification of black fungus spores. However, a large
amount of data is an essential prerequisite for its effective application. In
pursuing this idea, we developed a new novel fungus dataset of its kind, with
the goal of advancing the state-of-the-art in fungus classification by placing
the question of fungus detection. This is achieved by gathering various images
of complex fungal spores by extracting samples from contaminated fruits,
archives and lab incubated fungus colonies. These images primarily consisted of
five different types of fungus spores and dirt. The fungus detection system was
utilized to obtain these images. Which were further annotated to mark fungal
spores as a region of interest using specially designed graphical user
interface. As a result, 40,800 labeled images were used to develop fungus
dataset to aid in precise fungus detection and classification. CNN architecture
was designed and it showed the promising result with an accuracy of 94.8%. The
obtained results proved the possibility of early detection and classification
of several types of fungus spores using CNN and could estimate all possible
threats due to black fungus.
Existing System
All the above mentioned detection
methods have some limitation. Most of them are time consuming, laborious and
required well trained staff. Some of these methods required sophisticated and
very expensive equipment. Although we can get reliable, precise and effective
results by these aforementioned methods however these results and methods are
more probable to exhaust when we need to monitor immense volume i.e Container
of food items. Once the volume is massive like shipping containers, it’s nearly
impossible to seek out any trained professionals who can perform such a huge
task of monitor/ control microbes and resultantly, we have to just accept
potentially inaccurate results. In the process of fungal detection time is a crucial
factor. Considering time consuming procedures, expensive equipment, laborious
tasks and nevertheless inaccurate results warrants us to apply computer vision
and machine learning in this field which can render us with desired results.
Proposed System:
Most of the applications of artificial
intelligence are based on machine learning. Machine learning refers to that
machine, which can gain knowledge itself by study or experience. This means
that machine learning systems goes through several learning phases to achieve
better results. Machine learns from external information or input, accordingly
machine keeps on improving its program or structure to enhance its performance.
Usually, It is a normal practice to train machines on available existing data.
Subsequently the trained machine will be used to obtain desired output on new
data or test data. Instead of using pre-defined set of instructions the machine
is trained using huge amount of training data with the help of learning
algorithm which gives machine the learning ability. Figure 5.1 shows the
general architecture of machine learning process.
SYSTEM
REQUIREMENTS
HARDWARE REQUIREMENTS:
•
System : Pentium IV 2.4 GHz.
•
Hard Disk : 80 GB.
•
Monitor : 15 VGA Color.
•
Mouse : Logitech.
•
RAM : 2 Mb.
SOFTWARE REQUIREMENTS:
·
Operating system : Windows 10.
·
Platform :
PYTHON TECHNOLOGY
·
Tool :
Spyder, Python 3.5
·
Front End : Anaconda
·
Back End :
python anaconda script
0 Comments