First Prototype of Aquatic Tool Kit: Towards Low-Cost Intelligent Larval Fish Counting in Hatcheries

Loh, Brian Chung Shiong; Raman, Valliappan; Then, Patrick

doi:10.1109/dasc.2011.53

Cited by 6 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zheng and Zhang proposed a new method of counting fish using a digital image processing and a fuzzy artificial neural network (ANN) [21]. The method was capable of recognizing overlapped and differently sized fish.Loh, Raman, and Then developed Aquatic Tool Kits (ATK) for estimating the number of larval and juvenile fish using pixel counting [2]. However, the proposed method might not be flexible to count Fish of various size as the average area of a single larva is used to obtain the count In another study, Labuguen et al proposed an automated system using edge detection for fish fry counting and behavior analysis [13].…”

Section: Related Workmentioning

confidence: 99%

“…Also, its consumption has dramatically increased from approximately 36.82 million tons circa 1960 to 199.74 million tons by 2015 [1]. Likewise, the demand for aquaculture software, supplies, and equipment has increased-it was estimated to exceed US$ 80 billion in 2016 [1][2][3]. In Nigeria, catfish production has increased from 3 million tons per annum in 2001 to more than 30 million tons per annum in 2006 [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Recognition in Catfish Counting Algorithm Using Artificial Neural Network and Geometry

2020

KSII TIIS

View full text Add to dashboard Cite

One major and time-consuming task in fish production is obtaining an accurate estimate of the number of fish produced. In most Nigerian farms, fish counting is performed manually. Digital image processing (DIP) is an inexpensive solution, but its accuracy is affected by noise, overlapping fish, and interfering objects. This study developed a catfish recognition and counting algorithm that introduces detection before counting and consists of six steps: image acquisition, pre-processing, segmentation, feature extraction, recognition, and counting. Images were acquired and pre-processed. The segmentation was performed by applying three methods: image binarization using Otsu thresholding, morphological operations using fill hole, dilation, and opening operations, and boundary segmentation using edge detection. The boundary features were extracted using a chain code algorithm and Fourier descriptors (CH-FD), which were used to train an artificial neural network (ANN) to perform the recognition. The new counting approach, based on the geometry of the fish, was applied to determine the number of fish and was found to be suitable for counting fish of any size and handling overlap. The accuracies of the segmentation algorithm, boundary pixel and Fourier descriptors (BD-FD), and the proposed CH-FD method were 90.34%, 96.6%, and 100% respectively. The proposed counting algorithm demonstrated 100% accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%