(Final) Development of Image Analysis and Compression System - 2

A
PROJECT PROPOSAL
ON
DEVELOPMENT OF IMAGE ANALYSIS AND COMPRESSION SYSTEM
BY
ELIJAH GODWIN BASSEY

18/SC/CO/631
DEPARTMENT OF COMPUTER SCIENCE
UNIVERSITY OF UYO
SUBMITTED TO
DR. E. N UDO
B.SC PROJECT COORDINATOR
DEPARTMENT OF COMPUTER SCIENCE
UNIVERSITY OF UYO
JULY 2023
1.0 INTRODUCTION
Image processing was created in the 1960s with the introduction of digital
computers, focusing on noise removal and enhancement. The Discrete Fourier
Transform (DFT) is one of the most cutting-edge image analysis techniques.
Effective compression techniques were created as a result of the limited
transmission and storage capabilities of computers at the time. The Joint
Photographic Experts Group (JPEG) standard, which was introduced in 1992,
revolutionized the compression of digital pictures. In the 1980s and 1990s, many
compression techniques were developed to boost output and picture quality for a
range of applications.
Since the 1970s, feature extraction and detection approaches for image analysis
have advanced. Advanced methods including object identification, computer
vision, and picture segmentation were available in the 1990s, opening the door
for applications in robotics, security systems, and autonomous vehicles.
Convolutional neural networks in particular have revolutionized picture analysis
and compression by enabling image size reduction without sacrificing visual
quality.
An image is a two-dimensional message that the human visual system interprets.

Images are often represented by analogue impulses. For processing, storing, and
transmitting, computers need analog-to-digital conversion, Sindhu, M., &
Rajkamal, R. (2009).By reducing the amount of storage space needed for
photographs and videos, image compression enhances the efficiency of storage
and transmission.
In the past, image analysis research has generally been done inside the computer
science community and has mainly focused on basic pictures for applications like
defect detection, segmentation, and classification. Because it can now be done
more easily, quickly, and affordably, image analysis is becoming more and more
significant and common (Prats-Montalba'n et al. 2011). Machine vision
technology is frequently utilized in image analysis (Aguilera and Stanley 1999).
Digital image analysis has advanced significantly as a result of the rapid
development of hardware platforms and software frameworks.
There are several scientific and technological sectors where image analysis has
been used. For instance, it has been used to evaluate or measure the internal
structures and the exterior qualities (such as colour, size, form, and surface
texture) food goods' (architecture and/or connection of the material components).
1.1 STATEMENT OF PROBLEM
Large picture datasets are difficult to store and transmit due to the rising need for
image processing in high traffic applications including surveillance systems,
social media platforms, and multimedia content delivery networks. This project
suggests creating a cutting-edge software programme that combines powerful
picture analysis tools with effective compression methods to address these
problems.
1.2 AIMS AND OBJECTIVES OF THE PROJECT

The aim of this project is to develop an image analysis and compression system
by leveraging the power of existing tools like pillow, OpenCV python and PIL
capable of becoming a software as a service(SASS) solution serving enterprises
around the globe and integrated on demand with cloud delivery systems like
AWS S3 buckets, Cloudinary and google buckets.
The objectives of this project are:

1. To enable the system to efficiently handle diverse image formats by leveraging
the power of pillow and PIL image library for compression and optimization.
2. To create an independent server for autonomous operation to allow a plugable
solution as batteries on demand.
3. Deploy the server in a cluster environment to allow scalability using the concepts
of load balancing and distribution between master and slave nodes in the cluster.
4. Provide a versatile and robust solution for image manipulation by using the
power of C-level API calls available in OpenCV for analysis.
5. Ensure scalability and resource efficiency by employing the concept of multi
processing using python multiprocessing executor.
1.3 RESEARCH METHODOLOGY
To achieve the aim and objectives of this project,the following methodology will
be used:
1. The Pydantic and JSON-based config parser module will be developed to handle
system configurations efficiently allowing for a one time resource referencing.
2. The API interface module will be created using FastAPI and Uvicorn to provide
a robust and scalable RESTful interface for the system where consumers can
interact with the core system functionalities.
3. The core system module will be built around essential components like Pillow
and Gevent to handle image processing tasks and enable asynchronous
operations.
4. The Image Analyzer module will leverage OpenCV as the primary tool for
advanced image analysis, facial recognition and image dimensioning.
Open CV
Config Parser Core Analyzer
API Interface
Proposed System Architecture
1.4 SCOPE AND LIMITATION
The system's scope is focused on cloud deployments, allowing horizontal and

vertical scalability. It currently supports image compression, optimization,
rotation, upload, format conversion, cropping, and image streaming using buffer
rendering. The project aims to enhance the system with facial recognition
capabilities through image frame analysis and pattern matching for image
recognition. These expansions will enable facial identification, expression
analysis, and pattern/object recognition within images. The system provides
comprehensive image manipulation functionalities while being adaptable to cloud
environments, and the project aims to further enhance its capabilities in facial and
pattern recognition.
The project is limited by the requirement for a machine with a GUI, the
recommendation to avoid running it on single-core systems, and its CPU-
intensive nature that may not scale well with older CPU designs. Access to a
GUI-enabled machine is necessary for proper functioning, while single-core
systems may experience performance issues. The project is optimized for multi-
core architectures, utilizing parallel processing. Older CPU designs may not
possess the required computational power or instruction sets, affecting
performance and scalability. Consideration of these limitations is important to
ensure optimal performance and scalability of the system.
1.5 DEFINITION OF TERMS
The following terms are defined below:
Image compression: This is the reduction of the memory requirements by

removing the redundancy present in an image, that is, the image information
which is not perceptible to the human eye.
Image analysis: This returns numeric values and/or graphical information about
the image characteristics that are suited for classification, defect detection, or
prediction of some of the quality properties of the imaged object.
Image processing: This consists of improving the visual quality of the image by
reducing noise, pixel calibration and standardization, enhancing the edge
detection, and making the image analysis step more reliable based on objective
and well established criteria
REFERENCES
1. Richa Goyal, Jasmeen Jaura, “A Review of Various Image Compression

Techniques”, International Journal of Advanced Research in Computer
Science and Software Engineering, Volume 4, Issue 7, July 2014.
2. Harpreet Kaur, Rupinder Kaur, Nvdeep Kumar, “Review of Various
Techniques for Medical Image Compression”, International Journal of
Computer Applications, Volume 123, No. 4, Auguset 2015.
3. Bhonde Nilesh, Shinde Sachin, Nagmode Pradip, D.B. Rane, “Image
Compression Using Discrete Wavelet Transform”, IJCTEE, Volume 3,
March-April 2013.
4. A. Alarabeyyat, S. Al-Hashemi, T. Khdour, M. Hjouj Btoush, S. Bani-
Ahmed,R. Al-Hashemi, “Lossless Image Compression Technique Using
Combination Methods”, Journal of Software Engineering and Applications,
2012.
5. Malwinder Kaur, Navdeep Kaur, “A literature Survey on Losllless Image
Compression”, Internatiional Journal of Advanced Research in Computer
and Communication Engineering, Vol., 4, Issue , March 2015.
6. Sindhu, M., & Rajkamal, R. (2009). Images and its compression
techniques-A Review. International Journal of Recent Trends in
Engineering, 2(4), 71.
7. Arora, K., & Shukla, M. (2014). A comprehensive review of image
compression techniques. International Journal of Computer Science and
Information Technologies, 5(2), 1169-1172.
8. Mendoza, F., & Lu, R. (2015). Basics of image analysis. Hyperspectral
imaging technology in food and agriculture, 9-56.
9. Gunasekaran S, Ding K (1994) Using computer vision for food quality
evaluation. Food Technology 6:151–154

(Final) Development of Image Analysis and Compression System - 2

Uploaded by

Document Informationclick to expand document information

Copyright:

Available Formats

(Final) Development of Image Analysis and Compression System - 2

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

(Final) Development of Image Analysis and Compression System - 2

Uploaded by

Copyright:

Available Formats

A

DEVELOPMENT OF IMAGE ANALYSIS AND COMPRESSION SYSTEM

ELIJAH GODWIN BASSEY

An image is a two-dimensional message that the human visual system interprets.

1.2 AIMS AND OBJECTIVES OF THE PROJECT

The objectives of this project are:

1.3 RESEARCH METHODOLOGY

Proposed System Architecture

1.4 SCOPE AND LIMITATION

The system's scope is focused on cloud deployments, allowing horizontal and

1.5 DEFINITION OF TERMS

The following terms are defined below:

Image compression: This is the reduction of the memory requirements by

1. Richa Goyal, Jasmeen Jaura, “A Review of Various Image Compression

You might also like