Paddy seed variety identification using T20-HOG and Haralick textural features

نویسندگان

چکیده

Abstract The seed is an inevitable element for agricultural and industrial production. non-destructive paddy variety identification essential to assure purity quality. This research aimed at developing a computer vision-based system identify varieties using multiple heterogeneous features, exploiting textural, external, physical properties. We captured the images without any fixed setup make user friendly both industry farmer levels, which can lead illumination problems in images. To overcome this problem, we introduced modified histogram oriented gradient (T20-HOG) feature that describe illumination, scale, rotational variations of image. also utilized existing Haralick traditional features dimensionality reduced by Lasso selection technique. selected are used train feed-forward neural network (FNN) predict variety. experiments conducted on two different datasets: BDRICE, VNRICE. Results our method shown terms four standard evaluation metrics, namely, accuracy, precision, recall, F_1 score, achieved 99.28%, 98.64%, 98.48%, 98.56% respectively. compared efficiency with studies. experimental results demonstrate proposed effective new state-of-the-art performance. And observed newly T20-HOG have major impact overall

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Vehicle Logo Recognition Using Image Matching and Textural Features

In recent years, automatic recognition of vehicle logos has become one of the important issues in modern cities. This is due to the unlimited increase of cars and transportation systems that make it impossible to be fully managed and monitored by human. In this research, an automatic real-time logo recognition system for moving cars is introduced based on histogram manipulation. In the proposed...

متن کامل

Pedestrian detection using HoG features

Human Detection in Images is a contemporary Computer Vision problem, still welcoming improved solutions. This subset area of object detection has seen many attempts made towards efficient implementation and in this project proposal we describe one based on Histogram of Oriented Gradients which proves to be superior than the rest in terms of both Detection rate and Error rate when using a Linear...

متن کامل

Music genre classification using LBP textural features

In this paper we present an approach to music genre classification which converts an audio signal into spectrograms and extracts texture features from these time-frequency images which are then used for modeling music genres in a classification system. The texture features are based on Local Binary Pattern, a structural texture operator that has been successful in recent image classification re...

متن کامل

Image Colorization Using Discriminative Textural Features

This paper presents a novel approach to scribblebased image colorization. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we extract the most discriminative features using linear discriminant analysis (LDA). After that, the whole image is projected onto a discriminative textural feature space. Our main contrib...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Complex & Intelligent Systems

سال: 2021

ISSN: ['2198-6053', '2199-4536']

DOI: https://doi.org/10.1007/s40747-021-00545-0