回上一畫面 ----市民農園研發服務團隊
人工智慧用於烹調機器菜色狀況自動判別之研究
A Study of Automatic Judgment of Food Color and Cooking
Conditions with Artificial Intelligence Technology
MOST 108-2221-E-035-069 -
2019/08/01 ~ 2020/07/31
計畫中文關鍵詞電腦視覺、人工智慧、烹調、影像處理
本計畫預期架構一套烹調機器菜色狀況自動判別之影像自動監控系統，並著重相關人工智慧之建立。本研究使用機器視覺及人工智慧演算法，即時檢視食物的煮熟程度，也避免食物有過熟的狀況。本研究計畫為期二年，在第一年中，利用智慧型電磁加熱裝置，透過影像處理的程式，能夠自動辨識出食物煮熟前、後的顏色，藉由本研究新創的烹調參數辨別食物在未煮熟、煮熟，過熟時的烹調狀況。研究中使用攝影機結合軟體進行開發，以即時影像處理技術進行顏色判別，經由參數計算，監控食物的烹飪狀況。
第二年，利用色彩空間的轉換，再使用人工智慧、Adaboost相關演算法進行精確的目標物背景分割與檢測分類，除了將菜葉從背景分離，並計算烹調熟度、烹調時的不均勻度、油光澤度及醬汁吸收度。利用顏色色差來判斷食物的烹調情況，讓烹調系統可以透過影像色澤分佈，來辨別是否要後續採取局部翻攪，或進行起鍋的烹調動作。
本計畫將與仿生科公司合作，驗證系統之正確性與強鍵性，結合創新的人工智慧演算法，以增加結果的精確度，誤判率降低到3 %以內。
本計畫之目的及可能產生對社會、經濟、學術發展等面向的預期影響性
本研究運用機器視覺觀察鍋內中的食物熟度是否足夠，利用機器視覺結合演算法來監控，以求能夠讓烹調機器達到色香味俱全的境界。本研究未來可與多功能料理的相關的商品相結合，例如：智慧料理鍋、電火鍋、食物真空包裝機，可自己攪拌的料理鍋，以及煮菜機等，開發出更進階的自動化技術。
計畫英文關鍵詞Computer vision; artificial intelligence, cooking; image processing
Abstract
In this
study, the machine vision and artificial intelligence algorithms were used to rapidly
check the degree of cooking of foods and avoid over-cooking of foods. Using a
smart induction cooker for heating, the image processing program automatically
recognizes the color of the food before and after cooking. This proposal
consists of the following two years: In the first year, the new cooking parameters
were used to identify the cooking conditions of the food when it is undercooked,
cooked, and overcooked. In the research, the camera was used in combination
with the software for development, and the real time image processing
technology was used to obtain the information of the color of the food, and
through parameters calculation, the cooking status of the food was monitored.
In the second year, using the color space conversion, Adaboost
algorithm, and artificial intelligence, the foreground segmentation was used to
separate the vegetables from the background, and the cooking ripeness, cooking unevenness,
oil glossiness, and sauce absorption were calculated. The image color
difference and the distribution were used to judge the cooking conditions of the
food, so that the cooking system can identify whether or not to adopt partial tumbling,
or to end a cooking operation. In addition, we can design a novel artificial
intelligence algorithm in the relative field with the help of Biorobot company, and the error rate will be reduced to 3%.
We believe this work can significantly help researchers working in the advanced
cooking devices.