4th International Workshop on New Approaches for


Multidimensional Signal Processing


NAMSP 2023

Technical University of Sofia, Sofia, Bulgaria

July 06-08, 2023

Plenary Speakers


Prof. Dr. Parvinder Singh, Full Professor, Department of Computer Science & Engineering, Deenbandhu Chhotu Ram University of Science & Technology, Murthal, Haryana, India


Title of Lecture:

Rice Leaves Disease Detection using Convolutional Neural Network Techniques


Abstract: The world’s population is expected to increase by 2 billion persons in the next 30 years, from7.7billion currently to 9.7 billion in 2050, and can peak at nearly 11 billion around 2100. Most ofthe world’s population regards rice as the primary grain, and it is the source of a substantial portion of total calories for over half the earth’s population.Like other plants, rice is susceptibleto diseases that may affect the quantity and quality of produce. It sometimes results in anywherebetween 20–40% crop loss production. Early detection of these diseases can positively affect theharvest, and thus, farmers would have to be knowledgeable about the various disease andhowtoidentify them visually. Even then, it is an impossible task for farmers to survey thevast farmlands daily. Even if this is possible, it becomes a costly task that will in turn increases theprice of rice for consumers. So, an automated system is needed, this research methodologyproposed a novel SS-PEDCNN-based rice plant disease detection with a severity assessment system. Initially, the contrast level of the input image is enhanced to avoid various factors, suchas illumination variations using CLT-DPHE. Then, the background of the input imageisremoved to reduce the complexity of the input image using SE-GMM. After that, the separateparts (i.e., stem, sheath, leaf) of the input plant by considering the outer shape of the input image, is segmented using CDSO-ARG; then, each part of the input image color is transformedbecausethe color is varying for different diseases. Then, based on the different color models of different parts, the input image is clustered as healthy and diseased. From the disease parts, the featuresare extracted, and the features are given as input to the SS-PEDCNN classifier, whichpredictsthe rice stem rot, rice sheath spot, rice sheath rot, bacterial leaf streak, leaf smut, rice kernel smut, rice sheath, blight, leaf scald, rice stack burn, and rice blast diseases. Fromthe disease, theseverity level is predicted by using POI with the fuzzy rule.


Biographical Notes:
Present position: Full Professor, Department of Computer Science & Engineering, Deenbandhu Chhotu Ram University of Science & Technology, Murthal, Haryana, India
Administrative experience: Dean Faculty of IT & CS, DCRUST, Murthal Chairperson CSED, DCRUST Murthal, Professor Incharge Security, DCRUST Murthal, Director PG Admission, DCRUST Murthal
Teaching experience: Total experience - 28 years, Presently working at Deenbandhu Chhotu Ram University of Science & Technology, Murthal, Haryana (India) (DCRUST), Completed 2 terms as Chairman, Department of Computer Science & Engineering, DCR University of Science & Technology, Murthal, Honorary Visiting Professor, University of Deusto, Spain, Worked on India Bulgraia Joint Project with Technical University of Sofia, Working in Collaboration with University of Deusto, Spain, Received two Patents (One International and One Indian) in the field of Security and Image Processing, Awarded two grants from DST and one from UGC for major projects, Organized International and National Workshops/Conferences in various cities of the world and delievered Keynote Address, Biography published in 27th edition of Marquis Who's is Who in World 2010 and all the subsequent editions, Inclusion in the Top 100 Engineers - 2012 by Cambridge, England, Published more than 100 Papers in International Journal and Conference Proceedings