Fang Yanru, Bai Hongyi, Sun Laijun, Hou Jingli, Che Yuhang
College of Electronics and Engineering, Heilongjiang University, Harbin, China.
Jiaxiang Industrial Technology Research Institute of Heilongjiang University, Jining, Shandong Province, China.
J Food Sci. 2025 Jan;90(1):e70003. doi: 10.1111/1750-3841.70003.
Bruises can affect the appearance and nutritional value of apples and cause economic losses. Therefore, the accurate detection of bruise levels and bruise time of apples is crucial. In this paper, we proposed a method that combines a self-designed multispectral imaging system with deep learning to accurately detect the level and time of bruising on apples. To enhance the accuracy of extracting bruised regions with subtle features and irregular edges, an improved DeepLabV3+ was proposed. More specifically, depthwise separable convolution and efficient channel attention were employed, and the loss function was replaced with a focal loss. With these improvements, DeepLabV3+ achieved the maximum intersection over union of 95.5% and 91.0% for segmenting bruises on two types of apples in the test set, as well as maximum F1-score of 97.5% and 95.2%. In addition, the spectral data of the bruised regions were extracted. After spectral preprocessing, EfficientNetV2, DenseNet121, and ShuffleNetV2 were utilized to identify the bruise levels and times and DenseNet121 exhibited the best performance. To improve the identification accuracy, an improved DenseNet121 was proposed. The learning rate was adjusted using the cosine annealing algorithm, and squeeze-and-excitation attention mechanism and the Gaussian error linear unit activation function were utilized. Test set results demonstrated that the accuracies of the bruising levels were 99.5% and 99.1%, and those of the bruise time were 99.0% and 99.3%, respectively. This provides a new method for detecting bruise levels and bruised time on apples.
苹果碰伤会影响其外观和营养价值，并造成经济损失。因此，准确检测苹果的碰伤程度和碰伤时间至关重要。本文提出了一种将自行设计的多光谱成像系统与深度学习相结合的方法，以准确检测苹果的碰伤程度和时间。为了提高提取具有细微特征和不规则边缘的碰伤区域的准确性，提出了一种改进的DeepLabV3+。具体而言，采用了深度可分离卷积和高效通道注意力机制，并用焦点损失替换了损失函数。通过这些改进，在测试集中，DeepLabV3+对两种苹果的碰伤区域进行分割时，实现了95.5%和91.0%的最大交并比，以及97.5%和95.2%的最大F1分数。此外，还提取了碰伤区域的光谱数据。经过光谱预处理后，利用EfficientNetV2、DenseNet121和ShuffleNetV2来识别碰伤程度和时间，其中DenseNet121表现最佳。为了提高识别准确率，提出了一种改进的DenseNet121。使用余弦退火算法调整学习率，并利用挤压激励注意力机制和高斯误差线性单元激活函数。测试集结果表明，碰伤程度的准确率分别为99.5%和99.1%，碰伤时间的准确率分别为99.0%和99.3%。这为检测苹果的碰伤程度和碰伤时间提供了一种新方法。
