It Could Be You

It Could Be You

Year：2022

Material：Software, printer, thermal paper, real-time generative video, installations variable

作品《這可能是你》以網路即時留言者暱稱作為搜尋臉部圖像的關鍵，藉由合成資料與機器學習，產出許多不同的臉孔以及假個資，創造出「這有可能是你」的情境假象，用以質問與顯現個人的數位足跡與龐大網路資料能夠作為軟體系統對於人類的想像。這種方式並非像透過光的折射，再藉由大腦的化學生理變化去理解畫面，而是藉由每一個Pixel dot（像素點），再經過演算方式的一連串處理，當電腦軟體將人形辨識為物件時，知道依據型態去定義人，再加上物件是否移動的邏輯，它能更確認這是個會動的人，而不是一個靜態的人型看板。軟體藉由參考行為與環境的參數及變化，增強對於物件或事件的定義。

作品源自2019年鄭先喻的個展｛同化者｝中無題作品之延伸，藉由網路伺服器端應用，搜尋並搜集地區性線上論壇與即時聊天室資訊，建立資料庫模型以及視覺產出。當網路鄉民一留言，系統運用發文或留言者的帳號去搜尋可能的個人資料與肖像照片，再藉由合成資料技術結合機器學習成像，產出一系列的假想個資。

觀眾將於現場觀看網路鄉民即時訊息，現場列印機裝置則定時將合成的個人資料列印產出。

The work "This Could Be You" uses the nicknames of online real-time commenters as key elements for searching facial images. Through synthetic data and machine learning, it generates various faces and fabricated personal information, creating a scenario of "this could be you." This is used to question and reveal individuals' digital footprints and how extensive online data can be utilized by software systems to imagine human characteristics. Unlike the way we understand images through the refraction of light and the subsequent chemical and physiological changes in the brain, this method involves processing each individual pixel dot through a series of algorithms. When the computer software recognizes a human form as an object and defines it based on patterns, along with logic to determine object movement, it can confidently identify it as a moving person rather than a static human-shaped signboard. By referencing parameters and variations in behavior and the environment, the software enhances its definition of objects or events.

As a continuation of the untitled works featured in CHENG Hsien-Yu‘s solo exhibition｛Assimilator｝ in 2019, It Could Be You employs internet servers to collect messages from regional online forums and chatrooms to create a database model and to generate visual images. When netizens post a message, the system will detect it and instantly search for any personal information and portraits available by the users’ IDs, with which it adopts and integrates the technology of synthetic data with machine learning to generate images as a series of imaginary and fictional personal data.

Apart from the real-time and on-site display of the instant messages posted by netizens around the digital world, the installation will also print out the synthetic personal data at regular intervals.