Abstract
It is important to maintain the quality of tomatoes in the market distribution process after harvest. This requires classification of the harvested into ripeness stages. This paper describes a real-time tomato ripeness classification system based on a deep learning model of single stage detection. The applied deep learning model follows the architecture of a convolutional neural network of a single stream, which demonstrates the fastest and most accurate performance in the object detection field. To validate the proposed method, a large-scale data set of 4,182 high resolution images was collected and used to train and test the deep learning model. The ripeness classification was performed was performed at a maximum computation speed of 97fps and with an average accuracy of 91.3%. This result indicates that the performance of the proposed system attained the level required for commercialization and application in the real work environment.
Abstract from the paper’s OpenAlex record, shown for indexing and research. Copyright remains with the authors or the publisher. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 3
Claim · model-written summary
The classifier reached a maximum speed of 97fps for tomato ripeness classification.
- Taxon
- tomato
Solanum lycopersicumt0 - Outcome
- computation speede0
- Direction
- maximume0
- Value
- 97fpse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The ripeness classification was performed was performed at a maximum computation speed of 97fps”
t0“Tomato Ripeness”
Claim · model-written summary
The classifier reached 91.3% average accuracy for tomato ripeness classification.
- Taxon
- tomatoSolanum lycopersicumt0
- Outcome
- accuracye0
- Value
- 91.3%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“with an average accuracy of 91.3%”
t0“Tomato Ripeness”
Claim · model-written summary
The authors considered tomato ripeness classification performance sufficient for commercial use.
- Taxon
- TomatoSolanum lycopersicumt0
- Outcome
- performance of the proposed systeme0
- Comparator
- level required for commercialization and application in the real work environmente0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the performance of the proposed system attained the level required for commercialization and application in the real work environment”
t0“Tomato Ripeness”