跳到主要內容

萬里雲:GOOGLE 機器學習系統 TENSORFLOW LITE 離線辨識圖片效率大增

之前,臉書「垃圾文界的一位美少年」粉專上瘋傳一張辨識女星的驗證圖片,難倒一票夏于喬、宋芸樺傻傻分不清網友;隨後跑出一堆惡搞驗證圖,甚至還有辨識透抽的版本出現,讓參戰的網友們玩得不亦樂乎。

近期大家會發現,在 Google 填寫表單或臉書身份認證時,CAPTCHA 驗證方式變得越來越多元,文末將補充精彩的演進史。其中最常出現的就是以上的圖片辨識九宮格,要使用者指認出不同圖片中的物件,而這個功能其實就是TensorFlow 應用之一。
前年Google發佈了TensorFlow物件辨識API,讓開發者更容易在同一張圖片中辨識及定位多個不同物件。TensorFlow目前採開放架構設計,並開源提供開發者取用,希望能提升物件、人臉或影像品質等深度學習的速率與準確度。

上個月Google I/O 2017年會上,深度學習系統又進一步邁向了本次的重頭戲--輕量版的TensorFlow Lite。此版本在Android行動裝置上也能發揮人工智慧功能,藉由行動處理器進行裝置端的端點運算,甚至能夠支援離線操作。根據Google測試結果,在MobileNets系統運算下,離線準確率在70.7%~89.5%之間,雖然相比還是不及連上雲端的94%,但也已經十分出色,且在速度與方便性上更勝一籌。

TensorFlow發表近兩年來,已經幫助研究人員、醫療人員、工程師、藝術家、學生等各行各業增進工作效率,應用範圍包含更精確的機器翻譯、早期皮膚癌檢測、防止糖尿病的失明併發症等,族繁不及備載,如今已被用於超過六千個開源資料庫,未來應用的層面勢必更廣泛,深度學習將帶來的效益值得期待。
目前的機器深度學習技術其實不只有 Google TensorFlow,Facebook 去年推出的手機版新功能--創意效果相機,可偵測人臉及變換相片材質的互動式玩法,靠的也是他們專為手機設計的機器學習框架 Caffe2Go。而上個月蘋果 WWDC 2017 發表會上推出Core ML,開始在 iOS 11內導入裝置端的端點運算學習模型,試圖降低在 iOS裝置運行機器學習的困難度,期待iPhone、iPad等行動裝置在效能上能有更高效的表現。

CAPTCHA 小教室


CAPTCHA

Completely Automated Public Turing test to tell Computers and Humans Apart,俗稱驗證碼,是一種區分用戶是電腦或人的公共全自動程式。

reCAPTCHA

提供「有意義」的驗證碼讓使用者辨識,可能是 Google 地圖街景中的模糊文字、掃描古籍中的文字片段等等,這樣的驗證碼可以讓使用者在輸入的同時,幫助典籍或資料庫數位化建檔,也就是讓每一個用戶幫忙做數位校稿的工作。

No CAPTCHA reCAPTCHA

使用者只要在「我不是機器人」(I’m not a robot)的方框中打勾,就可以完成判別。新的API也在行動裝置上進行實驗,例如要求使用者選擇和範例圖片中物體相同的所有圖片。Google表示,在手機上點選簡單的動物圖片會比輸入一串枯燥扭曲的文字更為容易。

Invisible reCAPTCHA

無需用戶互動,利用演算法便可分辨人類和程式,詳情可以參考 Google reCAPTCHA 官方網頁。

參考資訊


CAPTCHA 又有新突破,Google 正準備「Invisible reCAPTCHA」
https://security.googleblog.com/2014/12/are-you-robot-introducing-no-captcha.html
Android O beta is available today
https://techcrunch.com/2017/05/17/android-o-beta-is-available-today/
Google釋出全新TensorFlow物件辨識API:不僅可在手機運作,甚至不用聯網
https://www.bnext.com.tw/article/44980/google-tensorflow-object-detection-api
Supercharge your Computer Vision models with the TensorFlow Object Detection API
https://research.googleblog.com/2017/06/supercharge-your-computer-vision-models.html
Google 開源機器學習系統 TensorFlow 1.0 正式發表
https://technews.tw/2017/02/18/google-announcing-tensorflow-1-0/
Caffe2go:Facebook最新的深度學習框架
https://kknews.cc/zh-tw/tech/jvr3zmy.html

留言

這個網誌中的熱門文章

COSCUP 2025 Call for Participation, 議程軌與攤位即日起開放申請

Jump to English   COSCUP 2025的社群議程/攤位即日起開始接受申請,社群議程於3月22日截止申請,社群攤位於6月10號截止。請有興趣在今年與我們共襄盛舉的社群把握機會! 👉  申請加入 以下介紹如何在 COSCUP 籌辦議程軌或攤位的流程及注意事項。

Early Guide to Joining COSCUP 2025 

(Updated: Feb 13) Many people in the community are excited to find out how to participate in COSCUP 2025. We’ll share more updates soon, but here’s what we can share so far! You can join as a speaker, host a booth, organize a track, or become a sponsor. If you’re new to COSCUP, take a look at the article " COSCUP Unveiled " to learn more. Date and Location The event will take place at NTUST in Taipei, Taiwan, on a weekend in late July to early August, as usual. The planned dates for this year are August 9-10. Be a Speaker Our early bird Call for Proposals (CfP) is now opened!  If you have a presentation about open culture or open-source technology, we want to hear from you. Submitting early means you’ll hear back sooner about your proposal. Host a Booth Open-source communities can set up booths to display their work and interact with attendees. This is a great way to share your community’s projects and connect with others. Businesses that support open-source can also host a ...

COSCUP 2025 Early Bird Call for Proposals

  If you are passionate about open culture and open-source technology, no matter where you are, we welcome you to join COSCUP 2025! We designed the Early Bird Program to give you more time to prepare your talk after acceptance and to help international speakers plan their trip to Taiwan. If you prefer to organize things early, this program is just for you. We look forward to welcoming you back to COSCUP, reconnecting with the community, and sharing your valuable experiences. About COSCUP COSCUP is an annual conference organized by the Taiwanese open-source community since 2006. COSCUP aims to provide a platform to connect Open Source coders, users, and promoters while promoting FLOSS within the annual conference. The conference is free to attend and all the staff are volunteers. We had more than 3000 attendees last year, and there will be more this year. It is the biggest open-source gathering in Taiwan, and the attendees are mostly developers, some power users, and FLOSS promote...