A new methodology for estimating the grapevine-berry number per cluster using image analysis

  1. Aquino, A. 1
  2. Diago, M.P. 1
  3. Millán, B. 1
  4. Tardáguila, J. 1
  1. 1 Instituto de Ciencias de la Vid y del Vino
    info

    Instituto de Ciencias de la Vid y del Vino

    Logroño, España

    ROR https://ror.org/01rm2sw78

Journal:
Biosystems Engineering

ISSN: 1537-5110

Year of publication: 2017

Volume: 156

Pages: 80-95

Type: Article

DOI: 10.1016/J.BIOSYSTEMSENG.2016.12.011 SCOPUS: 2-s2.0-85012110571 WoS: WOS:000399854300009 GOOGLE SCHOLAR

More publications in: Biosystems Engineering

Metrics

Cited by

  • Scopus Cited by: 55 (24-02-2024)
  • Web of Science Cited by: 46 (28-10-2023)
  • Dimensions Cited by: 54 (06-01-2024)

JCR (Journal Impact Factor)

  • Year 2017
  • Journal Impact Factor: 2.132
  • Journal Impact Factor without self cites: 1.885
  • Article influence score: 0.496
  • Best Quartile: Q1
  • Area: AGRICULTURE, MULTIDISCIPLINARY Quartile: Q1 Rank in area: 9/57 (Ranking edition: SCIE)
  • Area: AGRICULTURAL ENGINEERING Quartile: Q2 Rank in area: 4/14 (Ranking edition: SCIE)

SCImago Journal Rank

  • Year 2017
  • SJR Journal Impact: 0.676
  • Best Quartile: Q1
  • Area: Animal Science and Zoology Quartile: Q1 Rank in area: 98/462
  • Area: Agronomy and Crop Science Quartile: Q1 Rank in area: 78/382
  • Area: Soil Science Quartile: Q2 Rank in area: 40/154
  • Area: Food Science Quartile: Q2 Rank in area: 80/360
  • Area: Control and Systems Engineering Quartile: Q2 Rank in area: 76/1217

Scopus CiteScore

  • Year 2017
  • CiteScore of the Journal : 4.5
  • Area: Animal Science and Zoology Percentile: 93
  • Area: Agronomy and Crop Science Percentile: 87
  • Area: Food Science Percentile: 87
  • Area: Soil Science Percentile: 83
  • Area: Control and Systems Engineering Percentile: 78

Journal Citation Indicator (JCI)

  • Year 2017
  • Journal Citation Indicator (JCI): 1.06
  • Best Quartile: Q1
  • Area: AGRICULTURAL ENGINEERING Quartile: Q1 Rank in area: 3/16
  • Area: AGRICULTURE, MULTIDISCIPLINARY Quartile: Q1 Rank in area: 11/71

Dimensions

(Data updated as of 06-01-2024)
  • Total citations: 54
  • Recent citations (2 years): 17
  • Field Citation Ratio (FCR): 12.98

Abstract

A new image analysis algorithm based on mathematical morphology and pixel classification for grapevine berry counting is presented in this paper. First, a set of berry candidates represented by connected components was extracted. Then, six descriptors were calculated using key features of these components, and were employed for false positive (FP) discrimination using a supervised approach. More specifically, the set of descriptors modelled the grapes' distinctive shape, light reflection pattern and colour. Two classifiers were tested, a three-layer neural network and an optimised support vector machine. A dataset of 152 images was acquired with a low-cost smart phone camera. Images came from seven grapevine varieties, 18 per variety, at the two phenological stages in the Baggiolini scale between berry set (named stage K; 94 images) and cluster-closure (named stage L; 32 images). 126 of these images were kept for external validation and the remaining 26 were used for training (12 at stage L and 14 at K). From these training images, 5438 true/false positive samples were generated and labelled in terms of the six descriptors. The neural network performed better than the support vector machine, yielding consistent Recall and Precision average values of 0.9572 and 0.8705, respectively. The presented algorithm, implemented as a smartphone application, can constitute a useful diagnosis tool for the in-the-field and non-destructive yield prediction and berry set assessing for the grape and wine industry. © 2017 IAgrE