Print ISSN: 2204-1990

Online ISSN: 1323-6903

Keywords : Image processing


Critical Review of Deep Learning Algorithms for Plant Diseases by Leaf Recognition

M. Jaithoon Bibi, Dr. S.Karpagavalli, A. Kalaivani

Journal of Contemporary Issues in Business and Government, 2021, Volume 27, Issue 5, Pages 720-729
DOI: 10.47750/cibg.2021.27.05.044

The identification and classification of the crop leaf diseases plays an essential role in the
cultivation. Plants are the livelihood. Peoples depend entirely on crops for the breathing of
their daily lives. Thus, suitable crop caring should take place. Most research suggests that
the quality of agricultural commodities can be restricted depending on different factors. Crop
diseases include microorganisms and pathogens. The leaf diseases not only reduce crop
growth, the cultivation is also destroyed. Several researchers have been identified crop
leaf diseases using image processing algorithms but it take more time for detection.
Therefore, advanced algorithms are required to identify and classify the crop leaf diseases
automatically with higher accuracy. There are different deep learning algorithms using crop
leaf images developed for automatically detecting the crop leaf diseases in an efficient
manner. In this article, a survey on different deep learning algorithms using image processing
for detecting and classifying the crop or plant leaf diseases is presented. Also, the merits and
demerits of the surveyed algorithms for crop leaves diseases identification are addressed in a
tabular form. Finally, a comprehensive analysis is concluded and future directions are
suggested to increase the accuracy of leaf diseases classification.

EFFICIENT EYE BLINK COMMUNICATION ASSISTANCE FOR PARALYZED PATIENTS

Sivakumar D; Ramkumar P; Sridhar V; Yamuna A; Shashi B

Journal of Contemporary Issues in Business and Government, 2021, Volume 27, Issue 3, Pages 1575-1590
DOI: 10.47750/cibg.2021.27.03.208

The research study presents a real time method based on some video and image processing algorithms for eye blink detection to voice conversion. The motivation of this study is to help the disabled people who cannot communicate with human. The Haar Cascade Classifier is used for face and eye recognition to gain details about the eyes and facial axes. In comparison, the same classifier is used to assess the relation among the senses like eye and axis of the face to position the eye based on haar like features. This proposes an effective eye detection system which uses the sensed face location. An efficient eye detection method is proposed which uses the position of detected face. Finally, an eye blink detection method is done based on eyelids movement whether it is open or closed and is used for controlling mobile phones. The study have designed a very low-priced device that coverts the eye blinks to voice message with more accuracy compared to existing system. The eye blinks that are detected can be helpful in applications such as health assistance, S.O.S, basic utility. Test results show that our proposed system for a distance of 35cm delivers a overall accuracy of 98% and a detection accuracy of 98%

AN EFFICIENT METHOD FOR EYE TRACKING BY PASSWORD VERIFICATION

Kamal Raj T; Yashaswini R; Ranjitha B M; Sumanth D; Varshitha N

Journal of Contemporary Issues in Business and Government, 2021, Volume 27, Issue 3, Pages 1628-1642
DOI: 10.47750/cibg.2021.27.03.213

Individual Identification numbers are generally utilized for client verification and security. Secret key verification utilizing PINs expects clients to genuinely include the PIN, which could be frail against mystery word breaking by methods for acquiring individual or private or warm area. Individual range affirmation with tolerant look based range zone methodsgives up no consistent impressions and consequently offers a dynamically protected riddle state segment choice. Look based verification alludes to finding the consideration area across consecutive picture edges, and following eye community after some time. Eye following is accomplished by distinguishing a similar eye includes over various picture outlines and connecting them to a specific eye. The estimations are pursued for eye affirmation including various motivations behind the face district, eye development quickly moving, and iris snags to pick their comfort for the notable applications. Eye-stare identification has been generally explored and introduced. The eye can't move as quickly as 30 movements for every second. This prompted proposing an upgrade to the eye tracking framework being introduced. Picture preparing game plan isolates the iris and learns the specific community for an eye, in this way conveying controlled signs with the assistance of a reference place. The signs are controlled at that point utilized with a situation of a mechanized stage through wise camera. This upgrade improved the CPU handling time prerequisites. This presents a paper with a consistent application for look based range passage, and eye attestation to follow the range seeing verification using a sensible camera