@davangereuniversity.ac.in
Assistant Professor Dept. of studies in computer science
Davangere University
B.E. in Computer science and engineering
M.Tech. in Computer science and engineering
Ph.D. Pursuing
Digital image processing, Computer Vision, Deep learning,
Scopus Publications
Scholar Citations
Scholar h-index
Anitha Arekattedoddi Chikkalingaiah, RudraNaik Dhanesha, Shrinivasa Naika Chikkathore Palya Laxma, Krishna Alabujanahalli Neelegowda, Anirudh Mangala Puttaswamy, and Pushkar Ayengar
Institute of Advanced Engineering and Science
Arecanut is one of Southeast Asia’s most significant commercial crops. This work aims at helping arecanut farmers get an estimate of the yield of their orchards. This paper presents deep-learning-based methods for segmenting arecanut bunch from the images and yield estimation. Segmentation is a fundamental task in any vision-based system for crop growth monitoring and is done using U-Net squared model. The yield of the crop is estimated using Yolov4. Experiments were done to measure the performance and compared with benchmark segmentation and yield estimation with other commodities, as there were no benchmarks for the arecanut. U-Net squared model has achieved a training accuracy of 88% and validation accuracy of 85%. Yolo shows excellent performance of 94.7% accuracy for segmented images, which is very good compared to similar crops.
Anitha A. C., R. , Dhanesha, Shrinivasa Naika C. L., Krishna A. N., Parinith S. Kumar, and Parikshith P. Sharma
North Atlantic University Union (NAUN)
Agriculture and farming as a backbone of many developing countries provides food safety and security. Arecanut being a major plantation in India, take part an important role in the life of the farmers. Arecanut growth monitoring and harvesting needs skilled labors and it is very risky since the arecanut trees are very thin and tall. A vision-based system for agriculture and farming gains popularity in the recent years. Segmentation is a fundamental task in any vision-based system. A very few attempts been made for the segmentation of arecanut bunch and are based on hand-crafted features with limited performance. The aim of our research is to propose and develop an efficient and accurate technique for the segmentation of arecanut bunches by eliminating unwanted background information. This paper presents two deep-learning approaches: Mask Region-Based Convolutional Neural Network (Mask R-CNN) and U-Net for the segmentation of arecanut bunches from the tree images without any pre-processing. Experiments were done to estimate and evaluate the performances of both the methods and shows that Mask R-CNN performs better compared to U-Net and methods that apply segmentation on other commodities as there were no bench marks for the arecanut.
R. Dhanesha, D. K. Umesha, C. L. Shrinivasa Naika, and G. N. Girish
IEEE
Arecanut is one of the important commercial crop of Agriculture sector. Agriculture sector plays important role towards the economic development of India. The market price of arecanut is determined by it's maturity level of the ripeness . Farmers often incur loss in profit due to the lack of expertise in judging the ripeness maturity level of the arecanut bunches before the harvest. In the recent years, image processing and computer vision based precision agriculture techniques has helped the farmers in identifying the ripeness quality of the crops. So, accurate segmentation of the arecanut bunches plays vital role in the automated identification of the arecanut ripeness maturity level. In this proposed work YUV, YCbCr, YCgCr, YPbPr and HSV color models are used to segment arecanut bunches. Dataset with 1017 images of arecanut bunch are used to conduct experiment and segmentation result of the each color model is evaluated using different segmentation performance metrics. Results of experiment clarifies, segmentation of arecanut bunches were efficient using YCgCr and HSV color models.
R Dhanesha, C. L. Shrinivasa Naika, and Y Kantharaj
IEEE
Arecanut is profit-oriented crop of south India. In the market maturity level decides the price of Arecanut. To enhance the profitability identifying maturity level of Arecanut before harvesting is indispensable. Farmer need expertise to determine maturity level otherwise they get less profit for their crops. In recent times Computer Vision and Image Processing techniques are used in Precision Agriculture to identify the matured fruits and vegetables before harvesting. This paper proposes YCgCr color model to automatically segment the Arecanut bunch from a given image. Further, the segmented image could be used to determine Arecanut maturity level. Experiments were conducted to evaluate the efficacy of the segmentation method and found that the average Volumetric Overlap Error (VOE) is - 0.30 and Dice Similarity Coefficient (DSC) is 0.81.
R. Dhanesha and C. L. Shrinivasa Naika
Springer Singapore
Arecanuts are among the main commercial crops of southern India. Identifying ripeness is important for harvesting arecanut bunches and directly affects the farmer’s profits. Manual identification and harvesting processes, however, are very tedious, requiring many workers for each task. Therefore, in recent years, image processing and computer vision-based techniques have been increasingly applied for fruit ripeness identification, which is important in optimizing business profits and ensuring readiness for harvesting. Thus, segmentation of arecanut bunches is required in order to determine ripeness. There are several techniques for segmenting fruits or vegetables after harvesting to identify ripeness, but there is no technique available for segmenting bunches before harvesting. In this chapter, we describe a computer vision-based approach for segmentation using active contouring, with the aim of identifying the ripeness of arecanut bunches. The experimental results confirm the effectiveness of the proposed method for future analysis.
R. Dhanesha and Naika C. L. Shrinivasa
IEEE
Arecanut is one of the commercial crop of south India. Arecanut maturity level decides its price in the market. To maximize the profitability, Farmer needs expertise to determine the maturity level of Arecanut. This lack of ability leads to low profit for their crops. Use of Image Processing and Computer Vision techniques in precision agriculture allowed farmers to take necessary steps to harvest by identifying the maturity level of fruits and vegetables. To identify maturity level segmentation of Arecanut bunches is required for automated expertise. In this paper, proposed a segmentation method to segment Arecanut bunches using HSV color model towards the view of identifying automatic maturity level of arecanut bunches. The results of experiment clarifies the proposed method effectiveness which is better to segment the arecanut bunches for future analysis.
1. Segmentation of Arecanut Bunches using HSV Color Model.
2. A Novel Approach for Segmentation of Arecanut Bunches Using Active Contouring.
3.Segmentation of Arecanut Bunches using YCgCr Color Model