Application of deep learning diagnosis for multiple traits sorting in peach fruit

Masuda, Kanae; Uchida, Rika; Fujita, Naoko; Miyamoto, Yukio; Yasue, Takahiro; Kubo, Yasutaka; Ushijima, Koichiro; Uchida, Seiichi; Akagi, Takashi

doi:10.1016/j.postharvbio.2023.112348

Cited by 6 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 3, the Conv2D layer with 32 filters (F) of size (3,3) and a stride (S) of (2,2), which cuts the image size in half, is the first layer in the pre-trained Inception v3 block. A Conv2D layer with 32 filters of size (3,3) and a stride of (1,1) also makes up the second layer. The third layer is a Conv2D layer with 64 filters of size (3,3) and a stride of (1,1).…”

Section: Model 2-inception V3mentioning

confidence: 99%

“…A Conv2D layer with 32 filters of size (3,3) and a stride of (1,1) also makes up the second layer. The third layer is a Conv2D layer with 64 filters of size (3,3) and a stride of (1,1). A MaxPooling2D layer (Max-PL) that cuts the image's size in half is added next.…”

Section: Model 2-inception V3mentioning

confidence: 99%

“…A MaxPooling2D layer (Max-PL) that cuts the image's size in half is added next. While the fifth layer has 192 filters of size (3,3) and a stride of (1,1), the fourth layer is another Conv2D layer with 80 filters of size (1,1) and a stride of (1,1). The following MaxPooling2D layer cuts the image in half.…”

Section: Model 2-inception V3mentioning

confidence: 99%

See 2 more Smart Citations

Coffee bean graded based on deep net models

Balakrishnan Jayakumari,

Koovamoola Mambilamthoda,

Stephen

et al. 2024

IJECE

View full text Add to dashboard Cite

Coffee is a widely consumed beverage, and sorting coffee beans is a critical process that ensures high-quality graded coffee products. Coffee beans were graded into nine grades in robusta types. To automate the grading process, a deep learning-based approach was developed using a large dataset of high-resolution images and data augmentation techniques. In contrast to previous studies focusing on robusta type graded into six coffee bean grads, our research extends this framework by employing robusta type into nine grades with an outperformed accuracy. The proposed work uses four deep learning models, namely residual network 34(Resnet34), inception version 3 (Inception v3), efficient network bayesian optimization (EfficientNet-B0), and visual geometry group-16(VGG-16), where trained and evaluated for coffee bean classification into nine grades. The EfficientNet-B0 model exhibited outperformed accuracy, achieving 100% in distinguishing good and bad coffee beans, even in challenging lighting and background conditions.

show abstract

Section: Model 2-inception V3mentioning

confidence: 99%

Section: Model 2-inception V3mentioning

confidence: 99%

See 1 more Smart Citation

Coffee bean graded based on deep net models

Balakrishnan Jayakumari,

Koovamoola Mambilamthoda,

Stephen

et al. 2024

IJECE

View full text Add to dashboard Cite

show abstract

“…An efficient classification process using supervised deep learning and robot positioning based on embedded PD-FLC [25] Real-time identification and classification of fruits Does not consider the occlusion of the fruit 6600 2023 Sorting of fresh tea leaf using deep learning and air blowing [26] It better solves the decline in recognition accuracy caused by the mixed grades of fresh tea leaves Only the use of simple cases is considered 6400 2023 Application of deep learning diagnoses for multiple trait sorting in peach fruit [27] Diagnosis is possible through RGB images without the need for complex equipment Unable to detect internal defects 1512…”

mentioning

confidence: 99%

ECLPOD: An Extremely Compressed Lightweight Model for Pear Object Detection in Smart Agriculture

et al. 2023

View full text Add to dashboard Cite

Accurate pear sorting plays a crucial role in ensuring the quality of pears and increasing the sales of them. In the domain of intelligent pear sorting, precise target detection of pears is imperative. However, practical implementation faces challenges in achieving adequate accuracy in pear target detection due to the limitations of computational resources in embedded devices and the occurrence of occlusion among pears. To solve this problem, we built an image acquisition system based on pear sorting equipment and created a pear dataset containing 34,598 pear images under laboratory conditions. The dataset was meticulously annotated using the LabelImg software, resulting in a total of 154,688 precise annotations for pears, pear stems, pear calyxes, and pear defects. Furthermore, we propose an Extremely Compressed Lightweight Model for Pear Object Detection (ECLPOD) based on YOLOv7’s pipeline to assist in the pear sorting task. Firstly, the Hierarchical Interactive Shrinking Network (HISNet) was proposed, which contributed to efficient feature extraction with a limited amount of computation and parameters. The Bulk Feature Pyramid (BFP) module was then proposed to enhance pear contour information extraction during feature fusion. Finally, the Accuracy Compensation Strategy (ACS) was proposed to improve the detection capability of the model, especially for identification of the calyces and stalks of pears. The experimental results indicate that the ECLPOD achieves 90.1% precision (P) and 85.52% mAP50 with only 0.58 million parameters and 1.3 GFLOPs of computation in the homemade pear dataset in this paper. Compared with YOLOv7, the number of parameters and the amount of computation for the ECLPOD are compressed to 1.5% and 1.3%, respectively. Compared with other mainstream methods, the ECLPOD achieves an optimal trade-off between accuracy and complexity. This suggests that the ECLPOD is superior to these existing approaches in the field of object detection for assisting pear sorting tasks with good potential for embedded device deployment.

show abstract