Hyperspectral Imaging: An Inside View of Food Quality

舌尖(jiān)上的(dí)中國，早已告別(bié)“吃飽就(jiù)行(háng)”的(dí)時(shí)代。如(rú)今，我們(mén)追求的(dí)是更高品(pǐn)質，更(gēng)安全(quán)放(fàng)心的食品。高光譜成(chéng)像技(jì)術作(zuò)為一(yī)種新興(xīng)的技術，它(tā)能像(xiàng)“火眼(yǎn)金(jīn)睛”一樣，穿透食(shí)品的表(biǎo)象，檢測(cè)其內(nèi)在(zài)的成分，品(pǐn)質(zhì)和安全(quán)狀況(kuàng)。下(xià)麵，讓(ràng)我們一起走(zǒu)進(jìn)高光譜(pǔ)成(chéng)像(xiàng)技術(shù)在(zài)食(shí)品(pǐn)行業的應用巡禮(lǐ)。

In China, the era of being satisfied with merely "having enough to eat" is long gone. Today, we pursue higher quality, safer, and more reliable food. As an emerging technology, hyperspectral imaging can penetrate the surface of food products—much like having "eyes that see beneath the surface"—to detect their internal composition, quality, and safety conditions. Below, let’s explore the applications of hyperspectral imaging technology in the food industry.

農產(chǎn)品的品質檢(jiǎn)測 / Quality Inspection of Agricultural Products

高光譜(pǔ)成(chéng)像(xiàng)在農(nóng)產(chǎn)品分選中，尤(yóu)其(qí)擅(shàn)長進行無損檢(jiǎn)測(cè)，發現(xiàn)肉眼難以(yǐ)察覺(jué)的(dí)內部損(sǔn)傷。例如，它(tā)可以(yǐ)檢測蘋果(guǒ)外表可(kě)能看不見的(dí)瘀傷或內部損(sǔn)傷，實現(xiàn)更精準(zhǔn)的(dí)分(fēn)級，提升產品(pǐn)價值(zhí)。這(zhè)種非破壞(huài)性的(dí)檢測方(fāng)式，能(néng)夠幫助生(shēng)產者剔(tī)除存在(zài)潛在質量(liáng)問(wèn)題的(dí)產品，提升整體的產(chǎn)品質量和市場競爭(zhēng)力(lì)。

Hyperspectral imaging excels in the non-destructive inspection of agricultural products, particularly in sorting operations. It can detect internal damage that is difficult to see with the naked eye. For example, it can identify bruises or internal defects in apples that are not visible externally, enabling more accurate grading and enhancing product value. This non-destructive testing method helps producers remove items with potential quality issues, thereby improving overall product quality and market competitiveness.

基(jī)於高光(guāng)譜(pǔ)的蘋果(guǒ)分選(xuǎn) / Hyperspectral-Based Apple Sorting

農(nóng)產品的感(gǎn)官(guān)特(tè)征(zhēng)評價 / Evaluation of Sensory Characteristics in Agricultural Products

感(gǎn)官特征，如(rú)糖度，酸度，硬度(dù)和(hé)成熟度(dù)，直(zhí)接影響(xiǎng)消(xiāo)費者對農產品的喜好(hǎo)。高光(guāng)譜成像(xiàng)技術在(zài)食品感官(guān)評(píng)價中(zhōng)展現出(chū)巨(jù)大(dà)潛(qián)力，能夠(gòu)無損(sǔn)地(dì)預(yù)測(cè)這些關鍵指(zhǐ)標(biāo)。例如(rú)，通過分析柿(shì)子在(zài)特(tè)定(dìng)波(bō)長的反(fǎn)射率，可以(yǐ)建(jiàn)立(lì)澀(sè)味預測(cè)模(mó)型(xíng)；通過分析葡(pú)萄在(zài)近紅(hóng)外(wài)波段的光譜(pǔ)吸(xī)收特征，可(kě)以預測(cè)其糖(táng)度和(hé)酸(suān)度。與(yǔ)傳(chuán)統(tǒng)感(gǎn)官(guān)評價(jià)方法(fǎ)相比，高光譜成(chéng)像具有快速，客(kè)觀，無(wú)損的(dí)優(yōu)點(diǎn)。

Sensory attributes such as sugar content, acidity, firmness, and ripeness directly influence consumer preference for agricultural products. Hyperspectral imaging shows great potential in the sensory evaluation of food, as it can non-destructively predict these key indicators. For instance, by analyzing the reflectance of persimmons at specific wavelengths, a prediction model for astringency can be developed. Similarly, by examining the spectral absorption features of grapes in the near-infrared range, their sugar and acid levels can be predicted. Compared with traditional sensory evaluation methods, hyperspectral imaging offers the advantages of speed, objectivity, and non-destructiveness.

使(shǐ)用(yòng)高(gāo)光(guāng)譜(pǔ)技術(shù)實時在綫檢測葡萄(táo)糖(táng)度 / Real-Time Online Detection of Grape Sugar Content Using Hyperspectral Technology

茶葉品質評估 / Tea Quality Assessment

通(tōng)過(guò)分析(xī)茶(chá)葉的光譜(pǔ)信(xìn)息，可(kě)以無損(sǔn)，精(jīng)確(què)地分析茶(chá)葉(yè)中的(dí)生物活(huó)性成(chéng)分，如茶多酚(fēn)，咖啡鹼和氨(ān)基酸(suān)等(děng)，這些(xiē)成分對茶葉(yè)的風(fēng)味和(hé)品(pǐn)質至(zhì)關重(zhòng)要。某團隊利用高(gāo)光(guāng)譜數(shù)據建(jiàn)立了模型，可(kě)以(yǐ)準確估(gū)計茶(chá)葉(yè)中(zhōng)的茶(chá)多(duō)酚(fēn)含量。另一(yī)團(tuán)隊利(lì)用(yòng)無(wú)人(rén)機(jī)搭(dā)載的(dí)高光(guāng)譜相機(jī)，預(yù)測茶多酚和氨(ān)基酸(suān)含量(liáng)，並(bìng)評估(gū)茶(chá)多酚與氨(ān)基(jī)酸(suān)比值。

By analyzing the spectral information of tea leaves, key bioactive components such as tea polyphenols, caffeine, and amino acids—which are crucial to the flavor and quality of tea—can be assessed accurately and non-destructively. One research team developed a model based on hyperspectral data to accurately estimate the content of tea polyphenols. Another team used a drone-mounted hyperspectral camera to predict the contents of tea polyphenols and amino acids, and further evaluated the ratio between the two.

肉(ròu)品質(zhì)量評估 / Meat Quality Assessment

高光(guāng)譜成(chéng)像可(kě)準(zhǔn)確(què)測(cè)量脂(zhī)肪(fáng)和蛋(dàn)白質含(hán)量(liáng)，評估(gū)營養價(jià)值和風(fēng)味。例(lì)如(rú)，分析牛肉(ròu)大理(lǐ)石花紋(wén)預測嫩度(dù)和多(duō)汁(zhī)性，或評(píng)估魚類蛋白(bái)質(zhì)降解(jiě)程(chéng)度判斷新(xīn)鮮(xiān)度(dù)，區(qū)分(fēn)正(zhèng)常胸(xiōng)肉(ròu)和(hé)“木(mù)質(zhì)胸(xiōng)肉(ròu)”，它不(bù)僅能(néng)優化(huà)利用(yòng)率，還(huán)能(néng)檢測(cè)骨(gǔ)碎片(piàn)等(děng)異物，確(què)保食品安(ān)全(quán)。

Hyperspectral imaging can accurately measure fat and protein content, helping to evaluate nutritional value and flavor profiles. For example, it can analyze the marbling of beef to predict tenderness and juiciness, or assess the degree of protein degradation in fish to determine freshness. It is also capable of distinguishing between normal chicken breast and woody breast, and can detect foreign materials such as bone fragments—enhancing utilization efficiency while ensuring food safety.

利用高光(guāng)譜(pǔ)技術區分雞胸肉肉質(zhì) / Differentiating Chicken Breast Meat Quality Using Hyperspectral Technology

高光譜成像技術(shù)作為(wéi)新(xīn)興(xīng)的(dí)食品(pǐn)檢測手(shǒu)段，潛力(lì)巨大。盡管數據(jù)處理，設備成(chéng)本和應用場(cháng)景(jǐng)復雜性(xìng)帶來挑戰，但(dàn)人(rén)工智(zhì)能(néng)和機器學習(xí)的快速發展，為高(gāo)光譜(pǔ)成像技術帶來了(liǎo)新的(dí)機遇。通(tōng)過(guò)結(jié)合大(dà)數(shù)據分(fēn)析與建(jiàn)模(mó)，有望進一步提高食品品(pǐn)質預測的準確性，實(shí)現(xiàn)農產品等(děng)產(chǎn)業鏈的(dí)智(zhì)能化(huà)升級，從(cóng)生(shēng)產到加工(gōng)再(zài)到(dào)銷(xiāo)售，帶來更高效，更有品質保(bǎo)障(zhàng)的(dí)生(shēng)產模式。

As an emerging tool in food inspection, hyperspectral imaging holds significant potential. Although challenges remain in data processing, equipment costs, and the complexity of application scenarios, the rapid development of artificial intelligence and machine learning presents new opportunities for the technology. By integrating big data analysis and modeling, hyperspectral imaging is expected to further improve the accuracy of food quality prediction and enable intelligent upgrades across agricultural and food production chains—from production and processing to sales—paving the way for more efficient and quality-assured production models.