Apple defects can be divided into four main categories: mechanical damage, pathological disorders, contamination, and physiological disorders. These defects reduce the quality of apples, affect the sales price, and may be harmful to human health (Zhu et al., 2016; Lu and Lu, 2017). Apple bruises are typical mechanical damage that can easily occur during picking, sorting, packaging, and transportation (Van Zeebroeck et al., 2006; Xing et al., 2005). Identifying and classifying bruised apples as early as possible is conducive to the storage and circulation of apples. It can also prevent decaying and deteriorating apples from affecting other healthy apples (Zhang et al., 2017). Severe bruises can be identified with the naked eye or machine vision technology. However, early mild apple bruises, especially those occurring within half an hour, usually have no obvious external symptoms and are difficult to find (Keresztes et al., 2016; Lu et al., 2016). Therefore, it is necessary to find a fast, accurate, convenient and nondestructive discrimination method for apples with early bruises.
When the surface of an apple suffers mechanical damage, such as bumps, the pulp tissue is destroyed. The physiological metabolism of the damaged part will be disordered over time, the release of ethylene will increase, the respiratory strength will increase significantly, and the soluble solid content will be relatively reduced (Agar et al., 1999; Watada et al., 1996). In the initial stage of the bruises, under visible light, there is no obvious difference between the appearance of the bruised area and the healthy area; thus, a detection method based on visible light is subject to certain restrictions in this case. Due to the complex background and large discrepancies in the surface color, slight and early bruises are difficult to distinguish by image processing technology under visible light (Pan et al., 2019; Xing and De Baerdemaeker, 2007). The penetrability of near-infrared light in a tissue sample is deeper than that of visible light (Ding et al., 2021), and it is quite sensitive to changes in water content and soluble solids in the sample (Li et al., 2019; Takano et al., 2020). Therefore, a near-infrared image of an apple can more easily reveal bruising than a visible light image, which makes it possible for near-infrared imaging to identify early bruises in apples. Methods based on near-infrared imaging, including hyperspectral imaging and near-infrared camera imaging, have developed rapidly in recent years and are appropriate for the nondestructive detection of early bruises in apples.
Hyperspectral imaging technology integrates imaging, spectroscopy, chemometrics, and other optical sensing technologies. It is a nondestructive, noncontact detection technology that allows the simultaneous acquisition of sample spatial and spectral information (Xing and De Baerdemaeker, 2005; Al-Sarayreh et al., 2020). In recent years, hyperspectral imaging technology has been widely used to identify defects in various fruits, including the detection of early apple bruises (Lu et al., 2020). For example, Tan et al. (2018) used hyperspectral imaging combined with principal component analysis to identify early bruises in apples with a recognition rate of 99.9%. Luo et al. (2019) used hyperspectral and multispectral reflectance imaging technology to identify apple bruises within one hour, and the recognition rate reached 99.2%. Compared with other technologies, hyperspectral imaging technology not only reflects external characteristics such as the texture and size of the measured object but also reflects internal quality information such as the chemical composition content of the object (Lee et al., 2014). Since the information includes the spectral signature and the figure (Baranowski et al., 2013) is sufficient, hyperspectral imaging technology usually has a higher recognition rate. However, the three-dimensional data cube in this method has considerable redundant information, which increases the complexity of data processing (Du et al., 2017; Sui et al., 2015). Additionally, the calibration models are usually not independent of the particular calibration samples, measurement technique, or the setup of specific experiments.
Near-infrared camera imaging technology for identifying apple bruises is simple, fast, and highly sensitive. Near-infrared cameras have the advantages of small size, light weight, high luminous flux, and convenient data collection (Ge et al., 2016; Zhang et al., 2021). In conclusion, near-infrared imaging technology is suitable for the nondestructive detection of apple bruises. Aleixos et al. (2002) developed an imaging system based on a multispectral camera that can obtain visible light and near-infrared images from the same scene. The system can detect the size, color, and presence of defects in citrus and can also correctly classify lemons and citrus. Kleynen et al. (2003) proposed a method based on quadratic discriminant analysis that selects the best filter wavelength and constructs a multispectral imaging system to detect multiple defects in "Jonagold" apples. The combination of filters with three different wavelengths is sufficient to detect most bruised apples, and the combination of filters with four different center wavelengths has a classification accuracy of 100% for apples with severe defects and moderate defects. A near-infrared camera developed with T2SL material has a smaller dark current, lower noise, and higher sensitivity. It offers great target recognition and detailed expression under environmental conditions such as night vision and low visibility. For this reason, this study used a T2SL near-infrared camera with a wavelength range of 900–2350 nm to collect near-infrared images of bruised apple samples. A recognition method of apple bruises for detecting bruise edges was proposed, which could realize the nondestructive detection of early bruises (within half an hour) on apples. Bruised apples have lower reflectance than nonbruised apples in the visible light region, especially in the near-infrared light region. Thus, near-infrared images are more suitable for detecting bruises than visible light images.