Search

This work presents an automated and novel system for cricket commentary generation by the introduction of event driven approach and image captioning features. The presented system uses artificial intelligence and machine learning (ML) based methods to investigate real-time match data and generate real-time commentary by Image Captioning technique. For this purpose, deep neural network-based models and digital image processing techniques are used to detect the significant moments in the real-time match and generate commentary based on these real-time match events. The proposed method has been assessed using a dataset of 2 hours live cricket matches of India and England. After processing the match video, it has been observed that the developed model is successfully able to generate high-quality real-time commentary with a significant amount of accuracy. By commissioning leading-edge deep neural network-based model, the developed model determines the fitness to generate subtitles that are not only precise but also contextually appropriate, and efficiently apprehending the essence of the input frames. [ABSTRACT FROM AUTHOR]

India is one of the hugest rice cultivating country in the world. For thousands of years rice is a most major food, consequently every mankind depends on it directly and indirectly. But the Main hindrance in rice production is rice leaf diseases. It greatly reduces the production rate. Rice leaf diseases have specific symptoms that cannot be easily identified by usual human's eye. Using one of the image processing techniques, the rice leaf diseases are detected efficiently. In order to detect the diseased image Median Filter, K-means Clustering, GLCM and SVM classifier algorithms were proposed. Accuracy, Precision and ROC of SVM classifier were calculated as performance metrices. Around 97±2 % accuracy was achieved in this method. This paper discusses the efficient methodology for rice leaf disease detection. By using proposed method diseased leaves are identified at the early stage, which can aid farmers in preventing further damage to their crops. [ABSTRACT FROM AUTHOR]

The backbone of India and even most parts of the world is agriculture. Maintaining perishable farm produce is important to not to waste it, which will impact the economy and food starvation. This paper presents a mobile application for farmers or farm produce owners to check the ripeness of fruits and vegetables, which will be useful to make decisions on selling and fixing the price based on grading. The application provides information on different ripening stages of the fruits and vegetables. It also presents the information on crop's requirements for growth in terms of soil, nutrients, weather conditions, season, etc., as a reference manual. In this work, firstly, identification of different stages of ripening of perishable farm produce in field/cold storage using image processing is performed. Secondly, a mobile application is developed to give real-time status and notification of farm produce. The application will be updated with the images taken by CCTV or mobile cameras at definite intervals and notify the product owner well in time before rotting of the produce. The assessment of fruit quality is important for the cultivator and the consumer. Maturity detection is very important for fruit/ vegetable warehouses. This fruit maturity mobile application is named "Krishi Seva Bandhu". The results show that the detection accuracy is 90% and the mean opinion score of farmers is 85%. [ABSTRACT FROM AUTHOR]

Farmers grind away in the fields to take home just an exiguous income. Now, the agriculture industry is already a burdened industry with uncertainties from all directions. One of the major issues the industry is facing is crop loss. In India, every year around 30-40 per cent crops are lost. This has adverse effects on food security of the highly populated nation. For that matter, India is the 16th hungriest country in the world. Thus, there is a need to identify, understand and overcome agronomic losses. Extreme climate events and crop diseases are the two major reasons for crop losses. While climate events are less controllable, plant disease prevention becomes an important area of interest. Detecting plant diseases at early stages using images serves as key to preclusion of severity. In this paper, we have surveyed some of the significant papers on plant disease detection using image processing. [ABSTRACT FROM AUTHOR]

Now days the impact of climate change in India are mostly affected to the agriculture field, most of the agricultural crops are being badly affected in terms of their performance of the crop. The crop yield is used to predict in advance because of its harvest, its help the farmers for taking good decisions in marketing. The results of knowing crop yield and building prototype for the purpose of easily available to the farmer. Thus, for such kind of data analysis in the crop, there are different techniques and algorithms to predict the crop in a field. In this we have used image processing algorithm. The data used are images are taken from the drone system. Our approach starts by seeing rows inside the area (or acre) and finding all the trees in a crop yield, by this knowing the size of plant in the crop can be easily to store the data of plants. Lately there has been a wide source of spatial photogrammetry available for agriculture. Most of this data gives new information about the crops. By analysis of crop statics and methods have not been widely performed due to limitations on the images and software involved. The classification was also validated by comparing dozens of trees in the field, with excellent results. The purpose of this paper is to provide farmers with a method for quickly and automatically classifying trees by size, regardless of the presence or absence of problems, so that they can more easily monitor the health of individual trees and gain a better grasp on how those trees are distributed across a given area. [ABSTRACT FROM AUTHOR]