Digital Image Processing manifested to be a powerful tool for successful analysis in different areas and fields. Image processing with easy accessibility of corresponding system may alter the circumstance of gaining the advice of expert and at average cost since digital image-processing is the viable tool for examination of variables. Nowadays, computers are being utilized for automation, mechanization, expert system, Remote Sensing, Geographic Information systems and to develop a decision support system for taking vital choices on the protection research and agricultural production. This paper concentrate on the study of the importance and applications of Digital Image Processing in an agricultural area like Identification of Nutrient inadequacies and plant content, Fruits quality grading, sorting and inspection, Object tracking, land and crop management. The study presents a concise study of some of the current Digital Image Processing applications in the agricultural domain. The research findings indicate that from 2016 to 2024, the global 3D imaging market is expected to hit $26 billion, expanding at a CAGR of 23.7 per cent in global smart agriculture.
Agriculture is a significant part of an economy that gives essential needs and nourishment for
people. Advances in the area of innovation and science made another revolution in the agricultural
segment. The job of information technology has expanded the potential of the agricultural segment by
utilizing the automated system in different exercises [
India is a cultivating country; wherein about 70 per cent of the populace depends upon farming [
DIP method several tasks, such as image acquiring, preprocessing of images, segmentation of
images, extraction of features and classification. The steps are explained as follows in Fig. 1 [
Image Acquisition/Dataset: The first involves the acquisition of better qualitative images for achieving high accuracy as a suitable dataset is required for object recognition at every level.
Image Preprocessing:Preprocessing of images usually includes eliminating background noise, normalizing the intensity of individual pixels and eliminating reflections. Preprocessing basically enhance the images.
Image Segmentation: Segmentation divides image into various sections with solid relationship between the objects of interest. The outcome of image segmentation gives set of portions that jointly cover the whole image.
Feature Extraction:In this phase the essential features of region of interest of segmented images will be extracted and recognized based on color, texture and shape features.
Classification: In this final phase, data will be trained and tested.
Significance and effect of Image processing in society can be decided by its applications in various
fields like aerial and satellite imaging, industrial inspection, medical imaging, defense applications,
law enforcement and agriculture sector [
5. For finding outsize, variety and shape.
Nutrient inadequacies identification and plant content, Grading quality of fruits, sorting fruits and inspection, Object tracking, realm and crop estimation, Crop Management.
A) Identification of Nutrient inadequacies and plant content:
The lack of large scale (K, N, P, S, Ca and Mg) and small scale (Fe, Mo, Cl, Cu, B, and Zn)
minerals majorly affects plant advancement. Minerals majorly affect plant advancement [
B) Fruits quality grading, sorting and inspection:
Agriculture items are reviewed dependent on their measurements and quality. This evaluation is
utilized to sort them and appoint them to various sales channels. Everything may yield better pay
based when appropriately dispensed by its accurate attributes. Normally, higher evaluation and greater
farming items produce bigger incomes [
C) Object tracking, land and crop estimation:
Here in this study [14] Crop of Tobacco territory and yield estimates are significant in balancing out tobacco costs at the sale floors. The yield of tobacco estimation in Zimbabwe is presently founded on ground-based and statistical surveys. These strategies are expensive, tedious, and are inclined to huge mistakes. Remote detecting can give auspicious data on crop spectral qualities which can be utilized to appraise crop yields.
D) Crop Management:
Here in this for crop assessment using remote sensing weed detection is used, using pest management detection of insect has finished and for irrigation also used wireless sensor network. Phadikar, S., Sil, J. [15] the paper portrays a product model framework for disease detection of rice dependent on the contaminated images of different plants of rice. Piyush Chaudhary et al. [16] proposed an algorithm for sickness spot division utilizing the DIP technique in plant leaf. Yunseop Kim et al. [17] proposed an algorithm for “wireless sensor networks, software for real-time in-field sensing details of the instrumentation, software for real-time in-field sensing and design of variable rate irrigation, and control of a site-specific precision linear-move irrigation system”. Kamal N. Agrawal et al. [18] proposed the weed identification procedure utilizing an image processing system.
The Source of radiation in image processing was significant and the sources were X-ray imaging, UV band imaging, visible band imaging [19], imaging in Gamma-ray and IR band, Microwave band and Radio band imaging. The remote Sensing (RS) procedure was generally utilized for different applications in agriculture. Remote Sensing was the study of recognizable proof of earth surface highlights and estimation of geo-biophysical properties utilizing electromagnetic radiation. In image processing source of radiation was significant and the sources were X-beam imaging, imaging in the UV band, imaging in the Microwave band, Gamma beam imaging, imaging in the obvious band and IR band, and imaging in the Radio band. Thermal imaging which was a latent system (infrared lies between 3 to 14 μm) centers around Water. X-ray imaging for baggage inspection of stash nourishment items.
• • • • •
Visualization: Observe the items that are not imperceptible Image Restore and Sharpen: To build up a better image Estimation of Pattern: To estimate the several objects in image Image Recognition: Recognize the objects in a picture.
Image Retrieving:Find ROI in an image.
Agricultural sectors where the variables like quality, the canopy of the item are the important measures for the farmers. Most of the time advice of experts may not be reasonable and expert’s accessibility, as well as their administrations, may absorb time [20]. Image processing with easy accessibility of corresponding system may alter the circumstance of gaining the advice of expert and at average cost. During the present study it is evident that from 2016 to 2024, the global 3D imaging market is expected to hit $26 billion, expanding at a CAGR of 23.7 per cent (Figure: 3).
Digital Image Processing technique manifested as a successful Computer Vision framework for an agricultural area. Different applications of image processing have been talked about in detail imaging strategies with various ranges, these techniques are steady being developed for computerization models and acquiring higher precision of data. For example, Remote Detecting, Hyper Spectral Infrared Imaging help decide the vegetation records, cover estimation and so forth with more accuracy. Weed classification influences the capitulate (yield)can be effectively categorized with the algorithms of digital image processing. The classification accuracy ranges from 85%- 96% relying upon the limitations and algorithms of image acquisition. So, with these farmers can pertain herbicides in the right structure. The proposed methodology renders help in protecting the environmental factors. Hence, it can be conclude that Digital Image-Processing is an effective tool and a noninvasive method that can be related to the agricultural space with incredible accuracy for examination of different agronomic variables.
[14] X. Liming, Z. Yanchao (2010). Automated strawberry grading system based on image processing, Science Direct -Computers and Electronics in Agriculture, Volume 71, 32–39. [15] A. Rocha, D. C. Hauagge, J. Wainer, S. Goldenstein (2010). Automatic fruit and vegetable classification from images. Science Direct -Computers and Electronics in Agriculture, Volume 70, 96-104. [16] J. Blasco, N. Aleixos, S. Cubero, J. Gómez-Sanchís, & E. Moltó (2009). Automatic sorting of Satsuma (Citrus unshiu) segments using computer vision and morphological features. Science Direct -Computers and Electronics in Agriculture, Volume 66, 1-8. [17] Z. Jiang, Z. Chen, J. Chen, J. Liu, J. Ren, Z. Li, L. Sun, & H. Li (2014). Application of Crop Model Data Assimilation with a Particle Filter for Estimating Regional Winter Wheat Yields. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, Volume 07, Issue. 11. [18] E. Svotwa,& A. J. Masuka (2013). Remote Sensing Applications in Tobacco Yield Estimation and the Recommended Research in Zimbabwe. ISRN Agronomy, Volume 2013,1-7. [19] S. Phadikar, & J. Sil, (2008). Rice disease identification using pattern recognition techniques.
IEEE Computer and Information Technology, 2008. [20] P. Chaudhary, A. K. Chaudhari, A. N. Cheera, & S. Godara (2012). Color Transform Based Approach for Disease Spot Detection on Plant Leaf. International Journal of Computer Science and Telecommunications. Volume 03, Issue 06.