網購的名牌包包分不出真假？不用擔心，紐約初創公司Entrupy發明了一款小巧便攜的名牌包鑒定儀，它應用了顯微觀察和深度學習技術，拍攝的高清顯微圖像能呈現產品的材質、工藝以及序列號，然后再將這些照片和數據庫中3萬多款名牌包的圖片作對比，從而迅速判斷真偽。目前，Entrupy掃描儀可鑒定的產品僅限于名牌包，但是該技術幾乎可以應用于各種產品。

New York-based startup Entrupy has invented a small, portable scanner that rich people can use to check the authenticity of designer bags in mere seconds.
紐約初創公司Entrupy發明了一款小巧的便攜式掃描儀，它可以幫助土豪們在幾秒內檢測出名牌包包的真假。

According to data from the Organization for Economic Co-operation and Development, the global counterfeit industry is worth around 460 billion dollars, a big chunk of which involves counterfeit luxury goods from brands like Louis Vuitton or Channel.
據經濟合作與發展組織的數據顯示，全球造假行業的產值約為4600億美元，其中路易威登、香奈兒等大牌奢侈品的山寨貨占很大一部分。

The thing about such fakes is that they are often so well-made that the human eyes simply cannot tell them apart from originals. That's where technology comes in. Using a high-quality scanner and deep-learning technology, the brilliant minds behind Entrupy, have come up with a device that allows anyone to check the authenticity of luxury products, anytime, anywhere.
這類山寨產品的做工通常都很逼真，以至于肉眼幾乎無法分辨真假，這時候就需要借助科技了。Entrupy公司的人才們利用高品質掃描儀和深度學習技術，發明出這款可以隨時隨地鑒別奢侈品真偽的設備。

The Entrupy scanner connects to your smartphone and works in tandem with an app. The device is able to take high quality microscopic pictures of the material, processing, workmanship, and serial number of the product and then compare these images against a database of millions of photos of over 30,000 designer bags from the world's most popular brands. The deep learning technology behind Entrupy gets more accurate as clients upload more photos of authentic and fake bags to its database. Last year, Entrupy announced an authentication accuracy rate of 97%, and in August of this year, it had achieved an accuracy of 98.5%.
Entrupy掃描儀需連接智能手機，搭配應用軟件使用。這款設備能拍攝高清顯微圖片，呈現產品的材質、工序、工藝以及序列號，然后將這些照片和數據庫中3萬多款全球最火的名牌包圖片作對比。數據庫中包含了數百萬張圖片。用戶上傳到數據庫里的正品包和山寨包圖片越多，Entrupy的深度學習技術就越精準。去年，Entrupy公布的鑒定準確率為97%，今年8月其準確率已經達到98.5%。

Entrupy公司也表明，他們出具的鑒定結果客觀中立，而且他們與任何一家奢侈品公司都沒有關系。

“Entrupy's technology is a mix of machine learning and microscopy,” Ashlesh Sharma, Entrupy's co-founder, told Digital Trends. “We train our machine-learning algorithms to pick up data points from millions of microscopic images looking for qualities like texture, contrast, geometric shapes, thread counts, minor manufacturing artifacts such as scratches in the hardware stamps, wear, and many more details that you wouldn't be able to easily see. These details are in fed into our custom machine learning pipeline, allowing us to determine a product's authenticity. ”
Entrupy公司的聯合始人阿什萊斯?沙瑪對“數位趨勢”網站表示：“Entrupy結合了機器學習與顯微觀察技術。我們訓練機器學習算法從數百萬張顯微圖像中獲取數據點，分析紋理、對比度、幾何形狀、織物經緯密度以及五金件劃痕、磨損等諸多人眼難以觀測的細節。這些細節信息被輸入到專門的機器學習程序中，就能確定商品的真偽。”

Although Entrupy is currently limited to designer bags, the technology can be expanded to almost any type of product. The company has already tested it on a variety of goods, and is set to expand the functionality of the device in the near future.
目前，Entrupy掃描儀檢測的產品僅限于名牌包，但是該技術幾乎可以應用于各種產品。該公司已經在不同種類的商品上進行過測試，并預計在不久的將來擴大該設備的功能。

“The technology works pretty well on everything except for diamonds and porcelain, because those are refractive and we use optical analysis,” Entrupy CEO, Vidyuth Srinivasan, told Bloomberg.
Entrupy公司首席執行官斯里尼瓦桑對彭博社表示：“這種技術對所有商品都行之有效，不過鉆石和瓷器除外。因為這兩種物質會發生折射，而我們使用的是光學分析法。”

Entrupy doesn't sell their smart scanner and smartphone app, opting instead for a monthly lease system.
Entrupy并不銷售這款掃描儀及手機應用，而是選擇按月出租。

費用方面，目前主要有月付和年付兩種，前者99美元（約合人民幣647元）起，而后者950美元（約合人民幣6200元）起。在不同的付費方式下，根據不同的認證數量需求又有四種不同的選擇，月付費標準：

年付費標準：

Entrupy掃描儀已經成為越來越多企業的必備工具。據該公司介紹，目前已有160家典當店、批發商以及電商公司購買了相關服務。

英文來源：Oddity Central
翻譯&編輯：董靜
審校：丹妮