TW201227592A - Method for food and drink management with interactive image identifying technology - Google Patents

Method for food and drink management with interactive image identifying technology Download PDF

Info

Publication number
TW201227592A
TW201227592A TW99146965A TW99146965A TW201227592A TW 201227592 A TW201227592 A TW 201227592A TW 99146965 A TW99146965 A TW 99146965A TW 99146965 A TW99146965 A TW 99146965A TW 201227592 A TW201227592 A TW 201227592A
Authority
TW
Taiwan
Prior art keywords
food
image
database
nutrient
management
Prior art date
Application number
TW99146965A
Other languages
Chinese (zh)
Inventor
Ping-Hua Chang
Ting-Yi Tseng
Original Assignee
Ping-Hua Chang
Ting-Yi Tseng
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping-Hua Chang, Ting-Yi Tseng filed Critical Ping-Hua Chang
Priority to TW99146965A priority Critical patent/TW201227592A/en
Publication of TW201227592A publication Critical patent/TW201227592A/en

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The present invention relates to a method for food and drink management with an interactive image identifying technology, which includes following steps as a mobile phone or other similar hand-held electronic devices being used to capture image files for food, uploading the image files to an image server via Internet, acquiring image identifying parameters through the image identifying system of the image server in a manner of cloud computing, searching to confirm whether or not the image identifying parameters for food (including type, ingredient, quantity and size of food) built in the database, analyzing food nutrients of image identifying parameters via the nutrient database of the Internet, acquiring nutrient data and sending them back to users' mobile phones. Accordingly, users may realize what nutrients contain in the food they would like to eat at once, and take such data to be reference basis for their food and drink management. Still further, users can make their long-term personal records of nutrient absorbing amount of food and drink for management over their daily health.

Description

201227592 六、發明說明: 【發明所屬之技術領域】 [0001] 本發明係有關於一種互動式影像辨識技術之飲食營 理方法,尤其是指一種可隨時隨地的了解食物所含之營 養成分資料,以作為飲食管理之參考依據,並能建立個 人長期之飲食與營養攝取量之個人曰常生活健康管理紀 錄的飲食管理方法。 【先前彳支術】 [0002] 按,現有之飲食管理系統與方法,可參我國公開第 20090551 2號「營養吸收追蹤器」專利案,其 主要係提供一種協助營養資部•追雖之系統’包含:—標 記管理組件,其將一營養資訊合併灰一識別標記中;以 及一通信組件,係傳遞該營養資訊至一目標。 [〇〇〇3] 同時,第20090551 2號專利案提供—種追 縱營養資訊之電腦實施方法,包含·收集有關於一事件 的一營養資訊;合併該營養資訊至一識別碼中;以及一 旦該事件完成後,傳遞該識別瑪至一使用者。 [〇〇〇4] 此外,第2 〇 〇 9 〇 5 5 1 2號專利案尚提供一種 電腦可執行系統,包含:一mu河據裝I--,其係代表與在一事件期間所食用之複數個食品項目有 關的一營養資訊;以及/用於從該識別標記擷取該營養 資訊之裝置。 [0005] 上述之飲食管毽系統與方法在實際實施的時候,必 須先收集有關於一事件〔例如飲食吸收等事件〕的一營 養資訊,並〔可使用〆標記管理組件〕合併該營養資訊 099146965 表單編號 Λ0101 第 4 黃/共 16 頁 0992080728-0 201227592201227592 VI. Description of the Invention: [Technical Field of the Invention] [0001] The present invention relates to a method of diet management for interactive image recognition technology, and more particularly to an information about the nutrient content contained in a food at any time and anywhere. It is used as a reference for diet management and can establish a personal diet management method for personal long-term dietary and nutritional intake. [Previous sputum support] [0002] According to the existing diet management system and method, we can refer to the “Nutrition Absorption Tracker” patent case published in China No. 20090551 2, which mainly provides a system to assist the Ministry of Nutrition and Purchasing 'Contains: - a tag management component that combines a nutrition information into a gray identification tag; and a communication component that passes the nutritional information to a target. [〇〇〇3] Meanwhile, Patent No. 20090551 No. 2 provides a computer implementation method for tracking nutritional information, including: collecting a nutrition information about an event; combining the nutritional information into an identification code; After the event is completed, the identification is passed to a user. [〇〇〇4] In addition, the Patent No. 2〇〇9 5 5 1 2 2 provides a computer-executable system comprising: a mu river according to I--, which is representative of and consumed during an event a nutritional information relating to the plurality of food items; and/or means for extracting the nutritional information from the identification mark. [0005] In the actual implementation of the above-mentioned diet tube system and method, it is necessary to collect a nutrition information about an event (such as an event such as diet absorption), and [use the 〆 mark management component] to merge the nutrition information 099146965 Form No. Λ0101 4th Yellow/Total 16 Page 0992080728-0 201227592

[0006] Ο [0007] [0008] [0009] [0010] [0011] 至—識別碼中,透過使用者掃描該事件之識別碼,並將 此硪別石馬上傳或傳輸至一線上或雲端技術式遠端網路 以供後續針對營養調和之分析,並將該事件之營養資 :使用通信組件傳遞至—使用者。然而,如此之技術手 Μ糸僅能實施於已收集有營«訊之事件,即事先已編 。哉別碼的特定事件,而對於未事先編設識別碼的任意 事件,將無法透過此―系統架構查詢,故上述之飲食管 里系統與方法難以供使用者隨時隨地的了解任意事件之 營養資訊,降低了產業上之利用性。 【發明内容】 •本發明之主要目的,係提供一種互動式影像辨識技 術之飲食管理方法,其係直接透過㈣拍攝的食物影像 ’進行營養成分的分析’並回傳給使用者,以供使用者 能了解當下所欲食狀食物所含之營養成分,並依此作 為其飲食*r理之參考依據。同時,使用者可藉由此系統 ,建立起個人長期之飲食與營養攝取量記錄以建立個 人曰常生活之健康管理紀錄。 上述本發明之互動式影像_技術之飲食管理方法 的主要目❾’係由下列步驟達成: (a )建置營養成分資料於資料庫; (b )以掌上型裝置獲取食物之影像棺; (c )將影像槽透過網際網路上傳至影像舰器; =過影像词服器之影像辨識系統運算取得影像辨 099146965 表單編號A0101 第5頁/共16頁 201227592 [0012] ( e )辨哉系統檢索該影像參數是否内建於資料庫中; _3] ( f )辨識系統檢索該影像參數是否有内建之營養成分 資料庫; [0014] ( g )..·工辨識確認之食物影像參數與網站之營養資料庫 進行食品營養成分分析; [0015] (h)所付之營養成分資料回傳至掌上型裝置。 _] 根據本發明之互動式影像韻技術之飲食管理方法 較佳貝知例,在(b)「以掌上型裝置獲取食物之影像 檔」之步驟中,該影像稽的影像中係進—步包括一比例 參考物’ W作為該影像稽巾之食物影像的實際尺寸的來 考基準。 " 剛 減本發明之互喊f彡像辨識技術讀食管理方法 較佳實施例’在(d)「透過影像舰器之影像辨識系 統運异取得影像辨識之參數」之步驟中,係採用雲端運 算〔cl〇㈣comput ing〕之方式取得影 像辨識之參數;㈣掌上尊置無需内_識軟體,且 影像檔之辨識工作係由賴线執行,因錢達到效率 提升與成本降低之效果。 【實施方式】 酬 為令本㈣所運用之技術内容、發明目的及其達成 之功效有更完整且清楚的揭露,•下詳細說明之並 請一併參閱所揭之圖式及圖號: _ 首先’请參照第—圖所示,本發明之互動式影像辨 識技術之飲食管理方法係包括下列步驟: 099146965 表單編號A0101 第6頁/共16頁 201227592 [0020] [0021] 〇 [0022] [0023] [0024] ❹ (3 )建置營養成分資料於資料庫:係先在資料庫中建 各種食材之參數,以及各種食材參數中所含的基本營 養成分; (b )獲取食物之影像檔:請一併參照第二圖所示,其 係透過使崎動電料個人數位助理〔p e r s 〇 n a \dlgltal assistant, pDA 〕等掌上型裝置(1 )上所設之攝影器拍攝食物(2) 影像,以獲取該食物之影像檔; (c)將影像檔上傳至影像舰H :係於掌上型裝置( 4攝70成食物(2 ) &景彡像檔後,透過網際網路將 影像檔上傳至影像伺服器; (d )運算取得影像辨識之參數:係透過影㈣服器之 。像辨識Hx影像分析技術辨識該影像棺中食物(2 )之各個&材(;2 1 )’進而取得影像辨識之參數; )辨《哉系統檢索該影像參數是否内建於資料庫中: 辨為系統辨識丨該影像播之食物f彡像參數後 ,辨識系統 將檢索内建之資料庫巾是否有該食物影像參數〔或是最 吻合之食物影像參數〕,若有,係直接進入檢索營養成 刀步驟’否則由辨識系統傳訊至系統管理端,並由系統 管理端將該缺毛之食物影像參數手動㈣於資料庫中, 作為資料庫自主學f之經驗參數,並繼續進行下一檢索 營養成分之步驟; (f)辨識系統檢索該影像參數是否有内建之營養成分 貝料庫.辨識系統依據所得之影像參數再進一步檢索該 099146965 表單編號A0101 第7頁/共16頁 0992080728-0 [0025] 201227592 影像參數是否有内建之營養成分資料庫,若有,接續進 行下一步驟流程,否則由辨識系統傳訊至系統管理端, 並由系統管理端將該缺乏之食物營養成分手動建檔於資 料庫中,以作為資料庫自主學習之經驗參數,可助於往 後比對程序之順利進行; [0026] ( g )進行食品營養成分分析:經辨識確認之食物影像 參數與網站之營養資料庫進行食品營養成分分析; [0027] ( h )將營養成分資料回傳使用者:由辨識系統辨識出 該影像檔之食物影像參數並分析獲取該食物影像之營養 成分後,再將該些獲取得到之營養成分的數據透過網際 網路回傳至使用者之掌上型裝置(1)。此時使用者可 判斷該營養成分資料是否正確,若正確,即可供使用者 隨時隨地了解當下欲食用之食物(2 )之各個食材(2 1 )所含之營養成分資料,若不正確時,使用者可操作 掌上型裝置(1 )傳訊至系統管理端,由系統管理端手 動辨識正確之食物影像參數且建檔於資料庫中,再將正 確之使用者欲食用食物(2)的各個食材(2 1 )所含 的營養成分資料數據透過網際網路回傳至使用者之掌上 型裝置(1 )。 [0028] 其中,該營養成分資料係包括各個食材(2 1 )之 主要件〔是何種肉類或是何種蔬菜或其他〕與成分〔該 種肉類所含之成分〕等。 [0029] 其中,在(b ) 「獲取食物之影像檔」的步驟中, 可於該食物(2 )之旁側放置一硬幣,作為該食物(2 099146965 表單編號A0101 第8頁/共16頁 0992080728-0 201227592 [0030] Ο [0031] [0032]❹ 099146965 1之參考物(3),以供辨識系統依據該參考物 )的大小等比例判斷該食物⑵ 1)的份量。 何1 z 产’在(d)「運算取得影像辨識之參數將影像 ;至辨識系統」的步驟中,該影像檔係 减糸統以雲端運算〔cl 1豕辨 〕之方式取得影像辨識之細 ompu 11 ng 溝通多台電腦的二 端運算泛指運用網路 心換 或是透過網路連線取得由遠 知主機提供的服務等,亦即是說,掌上型裝=通 無需内建辨識軟體,且該影像檔之辨識工作 係 統執行,可藉由此種分散式運算 ,、辨識系 e d r n 逐异〔D 1 s t r i b u t 到M ……來處理魔大的資訊,以達 效率之提升與成本之降低。 再者,辨識系統食物影像參數,可為 中各個食材(21)之〇〜2 5 5㈣=析4像槽 5 5的RGf色度值等。 以下再進-步說明本發明實際實施之狀雜 視之方式拍攝-食物⑵ /先从俯 物(2)中之各個食材(21 =:】,並令該食 】均在鏡頭内,使該影像叛等 1),接著透過♦各個食材(2 上傳至_::=的食物(2)影像權 你、 景/像伺服器之影像辨識系統以导 析技_識姉像財食物(2 )之各個食〜 1),進而取得影像辨識之參數。當 2 檔之後將以影像分析技術辨識該影像檔;食物(二像 l=IQi213 =_數,此時辨識系統係ί 第9頁/共16頁 0992080728· 卜0 201227592 將影像檔中食物(2 )之各個食材(2 1 )作分割,並 針對該等食材(2 1 )之形狀、質地、色彩作辨識,且 分析該等食材(2 1 )之0〜2 5 5的R G B色度值, 待辨識系統辨識出該影像檔之食物影像參數後,辨識系 統將檢索内建之資料庫中是否有該食物影像參數〔或是 最吻合之食物影像參數〕,例如蛋、煻肉或米飯等之食 物影像參數,否則由辨識系統傳訊至系統管理端,並由 系統管理端將該缺乏之食物影像參數手動建檔於資料庫 中,若有該食物影像參數再與辨識系統所内建之資料庫 作比對,即可得該影像檔中食物(2)之各個食材(2 1 )所含之營養成分資料,接著辨識系統將營養成分資 料回傳至掌上型裝置(1),該營養成分資料係包括各 個食材(2 1 )之主要件〔例如燶肉為豬肉〕與成分〔 豬肉所含之成分〕等,此時使用者可判斷該營養成分資 料是否正確,若為正確者即可供使用者隨時隨地的了解 當下欲食用之食物(2)之各個食材(2 1 )所含之營 養成分資料而可作為飲食管理之參考基準,若該營養成 分資料不正確時,使用者可操作掌上型裝置(1 )而傳 訊至系統管理端,並由系統管理端手動辨識正確之食物 影像參數且建檔於資料庫中,而作為自主學習之經驗參 數,俾可供使用者進行長期之飲食管理以及健康管理。 [0033] 由上述之實施說明可知,本發明與現有技術相較之 下,本發明具有以下之優點: [0034] 1、本發明係以掌上型裝置獲取食物之影像檔並上傳至 辨識系統,且由辨識系統辨識出影像檔中食物所含之營 099146965 表單編號A0101 第10頁/共16頁 0992080728-0 201227592 養成分資料再回傳至掌上型敦置,以供使用者隨時隨地 的了解當下欲食用之食物所含之營養成分資料而可作為 飲食管理之參考基準。 [㈤35] 2、本發日祕可將該料養成分資料㈣應之食物影像 參數儲存於辨識系統所内建<資料庫中,以作為資料庫 自之經❹數’俾可供長期之飲食管理以及健康 管理。 [0036] 〇 [0037] [0038] ❹ [0039] 3、本發明係將影像播透過^運算之技術上傳至㈣系統’使得掌上型裝魏無^_識軟體且影像槽 之辨識工作係由辨齡統執行,料到效率之提升與成 本之降低。 、 以上所舉者僅係本發明之部份實施例,並非用 制本發明,致依本發明之創意精神及特徵,稍加變化修 飾而成者,亦應包括在本專利範圍之内。 綜上所述,本發明實施例確能達到所預期之使用功 效,又其所揭露之具體技術,不僅未曾見諸於同類技術 中,亦未曾公開於申請前,誠已完全符合專利法之規定 與要求’爰依法提出發明專利之申請’懇請惠予審杳 並賜准專利,則實感德便。 【圖式簡單說明】 第一圖:本發明之步驟流程圖 [〇〇4〇]第二圖:本發明之掌上型裝置拍攝狀態圖 【主要元件符號說明】 [0041] (1) 掌上型裝置 (2) 食物 099146965 表單編號Α0101 第11頁/共16頁 °99208〇728-〇 201227592 (3) 參考物 [0042] ( 2 1 )食材 099146965 表單編號A0101 第12頁/共16頁 0992080728-0[0006] [0010] [0011] In the identification code, the user scans the identification code of the event, and uploads or transmits the identification stone to a line or the cloud. The technical remote network is used for subsequent analysis of nutritional reconciliation and the nutrition of the event: the use of communication components to the user. However, such technical know-how can only be implemented in the event that has been collected and has been compiled in advance. Identifying specific events of the code, and for any event without prior identification code, it will not be able to query through this system architecture. Therefore, the above-mentioned system and method of eating and drinking is difficult for users to understand the nutritional information of any event anytime and anywhere. , reducing the utilization of the industry. SUMMARY OF THE INVENTION The main object of the present invention is to provide a method for managing foods by interactive image recognition technology, which directly transmits (by) the food image 'analysis of nutrient composition' and returns it to the user for use. The person can understand the nutrients contained in the current foods and use them as a reference for their diet. At the same time, users can use this system to establish a long-term personal and nutritional intake record to establish a healthy management record for a person's daily life. The above-mentioned interactive image-based technology management method of the present invention is achieved by the following steps: (a) building nutrient information in a database; (b) acquiring images of food by palm-type devices; c) upload the image slot to the image ship through the Internet; = image recognition system image acquisition system image acquisition 099146965 Form No. A0101 Page 5 / 16 pages 201227592 [0012] (e) Identification system Retrieving whether the image parameter is built in the database; _3] (f) identifying whether the image parameter has a built-in nutrient component database; [0014] (g).. The nutrition database of the website performs food nutrient analysis; [0015] (h) The nutrient information paid is transmitted back to the palm-type device. _] The food management method according to the interactive image rhyme technique of the present invention is better known. In the step (b) "Using a handheld device to obtain an image file of food", the image of the image is stepped into the image. A reference scale 'W' is included as a reference for the actual size of the food image of the image. " The preferred embodiment of the food-reading management method of the present invention has been reduced in the steps of (d) "parameters for obtaining image recognition through the image recognition system of the image ship" The cloud computing [cl〇(四)computing] method obtains the parameters of image recognition; (4) The palm respecting does not require the internal software, and the identification of the image file is performed by the Lai line, because the money achieves the effect of efficiency improvement and cost reduction. [Embodiment] Remuneration is a more complete and clear disclosure of the technical content, the purpose of the invention and the effects achieved by this (4). • Please refer to the drawings and drawings: _ First, please refer to the figure - the food management method of the interactive image recognition technology of the present invention includes the following steps: 099146965 Form No. A0101 Page 6 / Total 16 Page 201227592 [0020] [0021] 〇 [0022] [ 0023] [0024] ❹ (3) The establishment of nutrient information in the database: the parameters of the various ingredients in the database, and the basic nutrients contained in the various ingredients; (b) the image file for food : Please refer to the second picture together, which is to shoot food by the camera set on the palm-type device (1) such as the portable digital assistant (pers 〇na \dlgltal assistant, pDA) (2) Image to obtain the image file of the food; (c) upload the image file to the image ship H: after the palm-type device (4 photos 70% food (2) & landscape image, the image is transmitted through the Internet Upload files to the image server; ( d) Calculating the parameters of the image recognition: the image is transmitted through the image (4), and the Hx image analysis technology is used to identify the respective & materials (; 2 1 ) of the food (2) in the image file to obtain the parameters of the image recognition; The identification system retrieves whether the image parameter is built in the database: after the system identifies the image of the food image, the identification system will retrieve whether the built-in data library towel has the food image parameter [ Or the most consistent food image parameters], if any, directly enter the search nutrient forming step 'otherwise, the identification system communicates to the system management end, and the system management side manually (4) the hairless food image parameters in the database In the database, as the empirical parameter of the database self-learning, and continue the next step of searching for nutrients; (f) the identification system to retrieve whether the image parameters have built-in nutrient components, the library of the identification system based on the obtained image parameters Further search for the 099146965 Form No. A0101 Page 7 / Total 16 Page 0992080728-0 [0025] 201227592 Image parameters whether there is a built-in nutrient database, if any Continue to proceed to the next step process, otherwise the identification system communicates to the system management terminal, and the system management terminal manually files the lack of food nutrition components in the database as an empirical parameter for the independent learning of the database, which can be helpful The subsequent comparison procedure is carried out smoothly; [0026] (g) conducting food nutrient analysis: the identified food image parameters and the website's nutrition database for food nutrient analysis; [0027] (h) the nutrient data Returning the user: after identifying the food image parameters of the image file by the identification system and analyzing the nutrient components of the food image, the data of the obtained nutrients are transmitted back to the user's palm through the Internet. Type device (1). At this point, the user can judge whether the nutrient information is correct. If it is correct, the user can know the nutrient information contained in each food (2 1 ) of the food (2) that is currently consumed, if not correct. The user can operate the palm-type device (1) to communicate to the system management terminal, and the system management terminal manually recognizes the correct food image parameters and files in the database, and then the correct user wants to eat the food (2) The nutrient data contained in the ingredients (2 1 ) are transmitted back to the user's handheld device (1) via the Internet. [0028] wherein the nutrient composition data includes the main components of each food material (2 1 ), which kind of meat or vegetables or other ingredients, and the ingredients (the ingredients contained in the meat). [0029] wherein, in the step (b) "acquiring the image file of the food", a coin may be placed beside the food (2) as the food (2 099146965 Form No. A0101 Page 8 of 16 0992080728-0 201227592 [0030] 参考 [0032] 参考 099146965 1 reference (3), for the identification system to determine the amount of the food (2) 1) according to the size of the reference. In the step of (d) "calculating the image recognition parameters of the image; to the identification system", the image file system reduces the image recognition by cloud computing [cl 1豕] Ompu 11 ng The two-terminal operation of communicating with multiple computers refers to the use of network heart-switching or the provision of services provided by the remote host through the Internet connection, that is to say, the handheld device does not require built-in identification software. And the image file recognition work system is executed, and the decentralized operation can be used to identify the edrn divergence [D 1 stribut to M ... to process the information of the magic big, so as to achieve efficiency improvement and cost reduction. . Furthermore, the identification system food image parameter can be RGf chromaticity value of each of the ingredients (21) 〇~2 5 5 (4)=4 image groove 55. In the following, the following steps will be taken to illustrate the actual implementation of the present invention. The food (2) / first from the object (2) (21 =:], and the food is in the lens, so that Image rebellion 1), then through ♦ each food (2 upload to _:: = food (2) image right you, scene / image server image recognition system to guide analysis _ knowledge of food like food (2) Each food ~ 1), and then obtain the parameters of image recognition. After 2nd gear, the image file will be identified by image analysis technology; food (two images l=IQi213 = _ number, then the identification system is ί page 9 / total 16 pages 0992080728 · Bu 0 201227592 will be food in the image file (2 Each of the ingredients (2 1 ) is divided, and the shape, texture, and color of the ingredients (2 1 ) are identified, and the RGB chromaticity values of 0 to 2 5 5 of the ingredients (2 1 ) are analyzed. After the system to be identified recognizes the food image parameters of the image file, the identification system will retrieve whether the food image parameter (or the most consistent food image parameter) in the built-in database, such as eggs, meat or rice, etc. Food image parameters, otherwise the identification system communicates to the system management terminal, and the system management terminal manually files the lack of food image parameters in the database, if there is the food image parameter and the database built in the identification system By comparison, the nutrient data contained in each food (2 1 ) of the food (2) in the image file can be obtained, and then the identification system returns the nutrient data back to the palm-type device (1), the nutrient data Department includes each The main ingredients of the ingredients (2 1 ) (such as pork for pork) and ingredients (ingredients for pork), etc., at this time, the user can judge whether the information on the nutrient composition is correct, and if it is correct, it can be used by the user anytime, anywhere. The nutrient information contained in each of the ingredients (2 1 ) of the food to be eaten (2) can be used as a reference for diet management. If the nutrient information is incorrect, the user can operate the palm-type device (1) And the system is sent to the system management terminal, and the system management terminal manually recognizes the correct food image parameters and files them in the database, and as an empirical parameter of self-learning, the user can perform long-term food management and health management. [0033] It can be seen from the above description that the present invention has the following advantages compared with the prior art: [0034] 1. The present invention acquires the image file of the food by the palm-type device and uploads it to the identification system. And the identification system recognizes the camp contained in the image file. 099146965 Form No. A0101 Page 10 / Total 16 Page 0992080728-0 201227592 The palm-type can be used as a reference for food management by users who know the nutrient information contained in the foods they want to eat anytime and anywhere. [(5) 35] 2. The information of this ingredient can be used for this material (4) The food image parameters should be stored in the built-in <database of the identification system as a database for the long-term food management and health management. [0036] 〇[0037] [0038] ❹ [0039] 3. The invention uploads the video broadcast through the ^ computing technology to the (four) system 'making the palm-shaped device Wei no ^ _ knowledge software and the image slot identification work is performed by the age, and the efficiency is improved The cost is reduced. The above are only some of the embodiments of the present invention, and are not intended to be used in the present invention, and the modifications and variations of the present invention are also included in the scope of this patent. In summary, the embodiments of the present invention can achieve the expected use efficiency, and the specific technology disclosed therein has not been seen in the same technology, nor has it been disclosed before the application, and has completely complied with the provisions of the Patent Law. With the requirement of 'application for invention patents according to law', please review and grant patents. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a flow chart of steps of the present invention [〇〇4〇] FIG. 2: photographing state diagram of the palm-type device of the present invention [Description of main components] [0041] (1) Handheld device (2) Food 099146965 Form No. Α0101 Page 11 of 16 °99208〇728-〇201227592 (3) References [0042] ( 2 1 ) Ingredients 099146965 Form No. A0101 Page 12 of 16 0992080728-0

Claims (1)

201227592 七、申請專利範圍: 1 . 一種互動式影像辨識技術之飲食管理方法,係包含下列步 驟: (a )建置營養成分資料於資料庫, (b )以掌上型裝置獲取食物之影像檔; . (c )將影像檔透過網際網路上傳至影像伺服器; (d )透過影像伺服器之影像辨識系統運算取得影像辨識 之參數; (e )辨識系統檢索該影像參數是否内建於資料庫中; 〇 (f) 辨識系統檢索該影像參數是否有内建之營養成分資 料庫; (g) 經辨識確認之食物影像參數與網站之營養資料庫進 行食品營養成分分析; (h) 所得之營養成分資料回傳至掌上型裝置。 2.如申請專利範圍第1項所述之飲食管理方法,其中,在步 驟(b )中係以俯視之方式獲取該食物之影像檔。 ^ 3 .如申請專利範圍第1或2項所述之飲食管理方法,其中, ❹ 在步驟(b )中係進一步的於該食物之旁側放置一比例參 考物。 4 .如申請專利範圍第1項所述之飲食管理方法,其中,在步 驟(d)中係透過雲端運算〔c 1 oud comput i n g〕之技術取得影像辨識之參數。 5.如申請專利範圍第1項所述之飲食管理方法,其中,在步 驟(d)中係以影像檔中食物之RG B色度值進行辨識分 析。 099146965 表單編號A0101 第13頁/共16頁 0992080728-0 201227592 .如申請專利範圍第!項所述之飲食管理方法,其中,在步 2 ( e )中當辨識系統檢索營養資料庫中沒有該食物影像 參數〔歧最吻合之食物影像參數〕時,由辨識系統傳訊 至糸統管理端,並由系統管理端將該缺乏之食物影像參數 手動建播於資料庫中,以作為資料庫自主學習之經驗參數 〇 .如申請專利範圍第1項所述之飲食管理方法其中,在步 驟(f)中當辨識系統檢索營養成分資料庫而無相對該影 像參數之營養成分資料時,將則由辨識系統傳訊至系統管 理端,並由系統管理端將該缺乏之食物營養成分手動建樓 I 於資料庫中。 田 ’如申請專利範圍第1項所述之飲食管理方法,其中,在步 驟(h )中辨識系統將營養分資料回傳至掌上型裝置後 ’再由使用者判斷該營養成分資料是否正確,否則操作掌 上型裝置傳訊至系統管理端,並由系統管理端手動辨識且 建檔於資料庫中。 •如申請專利範圍第1或8項所述之飲食管理方法其中, 该掌上型裝置為行動電話及個人數位助 、y e r s ο η al digital assistant, PDA 〕中之任一種。 099146965 表單編號A0101 第14頁/共16頁 0992080728-0201227592 VII. Scope of application for patents: 1. A method of food management for interactive image recognition technology, which comprises the following steps: (a) building nutrient information in a database, and (b) obtaining image files of food by palm-type devices; (c) uploading the image file to the image server via the Internet; (d) obtaining the image recognition parameter through the image recognition system of the image server; (e) identifying whether the image parameter is built in the database ;(f) Identification system retrieves whether the image parameters have a built-in nutrient database; (g) food identification parameters identified by the identification and the nutrition database of the website for food nutrient analysis; (h) nutrition obtained The ingredient data is passed back to the handheld device. 2. The food management method according to claim 1, wherein in step (b), the image file of the food is obtained in a plan view. The dietary management method according to claim 1 or 2, wherein, in step (b), a proportional reference is further placed on the side of the food. 4. The food management method according to claim 1, wherein in step (d), the image recognition parameter is obtained by a technique of cloud computing (c1 oud comput i n g). 5. The food management method according to claim 1, wherein in step (d), the RG B chromaticity value of the food in the image file is used for identification analysis. 099146965 Form No. A0101 Page 13 of 16 0992080728-0 201227592 . The food management method according to the item, wherein, in step 2 (e), when the identification system does not have the food image parameter (the most consistent food image parameter) in the nutrition database, the identification system transmits the message to the management side of the system. And the system management terminal manually builds the lack of food image parameters into the database as an empirical parameter for the independent learning of the database. For example, the food management method described in claim 1 is in the step (f) When the identification system searches the nutrient composition database without the nutrient composition data of the image parameters, it will be transmitted from the identification system to the system management terminal, and the system management terminal manually builds the lack of food nutrients. I is in the database. The food management method according to the first aspect of the patent application, wherein in the step (h), the identification system returns the nutrient data to the palm-type device, and then the user judges whether the nutrient information is correct or not. Otherwise, the palm device is operated to communicate to the system management terminal, and is manually recognized by the system management terminal and archived in the database. The food management method according to claim 1 or 8, wherein the palm-sized device is any one of a mobile phone and a personal digital assistant, y e r s ο η al digital assistant, PDA. 099146965 Form No. A0101 Page 14 of 16 0992080728-0
TW99146965A 2010-12-30 2010-12-30 Method for food and drink management with interactive image identifying technology TW201227592A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW99146965A TW201227592A (en) 2010-12-30 2010-12-30 Method for food and drink management with interactive image identifying technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW99146965A TW201227592A (en) 2010-12-30 2010-12-30 Method for food and drink management with interactive image identifying technology

Publications (1)

Publication Number Publication Date
TW201227592A true TW201227592A (en) 2012-07-01

Family

ID=46933330

Family Applications (1)

Application Number Title Priority Date Filing Date
TW99146965A TW201227592A (en) 2010-12-30 2010-12-30 Method for food and drink management with interactive image identifying technology

Country Status (1)

Country Link
TW (1) TW201227592A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI498845B (en) * 2012-12-14 2015-09-01 Ind Tech Res Inst Method and system for diet management
TWI512282B (en) * 2014-04-03 2015-12-11 Tzu Shan Cheng A gem identification device and a gem image identification system
TWI620131B (en) * 2015-08-18 2018-04-01 財團法人工業技術研究院 System and method for object recognition
WO2018175354A1 (en) * 2017-03-19 2018-09-27 Charles Siebenberg Methods and systems for authenticating products

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI498845B (en) * 2012-12-14 2015-09-01 Ind Tech Res Inst Method and system for diet management
US9449029B2 (en) 2012-12-14 2016-09-20 Industrial Technology Research Institute Method and system for diet management
TWI512282B (en) * 2014-04-03 2015-12-11 Tzu Shan Cheng A gem identification device and a gem image identification system
TWI620131B (en) * 2015-08-18 2018-04-01 財團法人工業技術研究院 System and method for object recognition
WO2018175354A1 (en) * 2017-03-19 2018-09-27 Charles Siebenberg Methods and systems for authenticating products

Similar Documents

Publication Publication Date Title
Stumbo New technology in dietary assessment: a review of digital methods in improving food record accuracy
US9727565B2 (en) Photo and video search
CN105653636B (en) Information processing method and device for information processing
Carter et al. ‘My Meal Mate’(MMM): validation of the diet measures captured on a smartphone application to facilitate weight loss
CN103793450B (en) Message processing device and information processing method
IL255797A (en) Methods and systems of providing visual content editing functions
JP5814700B2 (en) Image processing system and image processing method
US20190221134A1 (en) Meal Management System
JP2011028382A (en) Nutrition management server and nutrition management method for managing nutrition component of meal for each user
WO2014168177A1 (en) Image processing device
TW201227592A (en) Method for food and drink management with interactive image identifying technology
Ahmad et al. A mobile phone user interface for image-based dietary assessment
US20210312181A1 (en) Image processing device, image processing method, program, and recording medium
CN107851183A (en) System and method for providing recipe
Lee et al. Aifood: a large scale food images dataset for ingredient recognition
Liang et al. CEP: calories estimation from food photos
US9875512B2 (en) Photo and video sharing
JP2019057245A (en) Information processing apparatus and program
US8972427B2 (en) System and method for providing electronic supplemental content associated with printed content in a printed publication
Aizawa Multimedia foodlog: Diverse applications from self-monitoring to social contributions
JP6513009B2 (en) IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, PROGRAM, AND RECORDING MEDIUM
Allman-Farinelli Using digital media to measure diet.
Shao et al. Semi-automatic crowdsourcing tool for online food image collection and annotation
Goyal et al. I ate this: A photo-based food journaling system with expert feedback
Dinic et al. EatAR tango: portion estimation on mobile devices with a depth sensor