Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cannabis Seed Variant Detection using Faster R-CNN

Toqi Tahamid Sarker, Taminul Islam, Khaled R Ahmed

TL;DR

This paper presents the first known application of a deep neural network-based object detection model to the novel task of visually identifving variants of cannabis seeds, using Faster R-CNN, a two-stage object detection model, to accurately detect and classify 17 distinct classes of cannabis seeds sourced locally in Thailand.

Abstract

Analyzing and detecting cannabis seed variants is crucial for the agriculture industry. It enables precision breeding, allowing cultivators to selectively enhance desirable traits. Accurate identification of seed variants also ensures regulatory compliance, facilitating the cultivation of specific cannabis strains with defined characteristics, ultimately improving agricultural productivity and meeting diverse market demands. This paper presents a study on cannabis seed variant detection by employing a state-of-the-art object detection model Faster R-CNN. This study implemented the model on a locally sourced cannabis seed dataset in Thailand, comprising 17 distinct classes. We evaluate six Faster R-CNN models by comparing performance on various metrics and achieving a mAP score of 94.08\% and an F1 score of 95.66\%. This paper presents the first known application of deep neural network object detection models to the novel task of visually identifying cannabis seed types.

Cannabis Seed Variant Detection using Faster R-CNN

TL;DR

This paper presents the first known application of a deep neural network-based object detection model to the novel task of visually identifving variants of cannabis seeds, using Faster R-CNN, a two-stage object detection model, to accurately detect and classify 17 distinct classes of cannabis seeds sourced locally in Thailand.

Abstract

Analyzing and detecting cannabis seed variants is crucial for the agriculture industry. It enables precision breeding, allowing cultivators to selectively enhance desirable traits. Accurate identification of seed variants also ensures regulatory compliance, facilitating the cultivation of specific cannabis strains with defined characteristics, ultimately improving agricultural productivity and meeting diverse market demands. This paper presents a study on cannabis seed variant detection by employing a state-of-the-art object detection model Faster R-CNN. This study implemented the model on a locally sourced cannabis seed dataset in Thailand, comprising 17 distinct classes. We evaluate six Faster R-CNN models by comparing performance on various metrics and achieving a mAP score of 94.08\% and an F1 score of 95.66\%. This paper presents the first known application of deep neural network object detection models to the novel task of visually identifying cannabis seed types.
Paper Structure (19 sections, 6 equations, 2 figures, 2 tables)

This paper contains 19 sections, 6 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Image processing in Seed Classification
  4. Machine learning in Seed Classification
  5. Deep Learning in Seed Classification
  6. Materials and Methods
  7. Cannabis Seed Dataset
  8. Dataset Preprocessing
  9. Training
  10. Faster R-CNN Network Architecture
  11. Loss Functions
  12. L1 loss
  13. IoU loss
  14. GIoU loss
  15. DIoU loss
  16. ...and 4 more sections

Figures (2)

  • Figure 1: Three different cannabis seed types. (a) AK47, (b) Gelato, and (c) Gorilla Purple.
  • Figure 2: mAP vs Inference Speed of Faster R-CNN Models