In Progress

Topic provider

In the past 40 years, the Electronic and Optoelectronic System Research Laboratories undertakes the missions for the researches and developments of Semiconductor, Packaging, LED/OLED/Micro LED, Telecommunications, Flexible Electronics, 3D Imaging, Flexible Display and Transparent Display Application System technologies.

ITRI provides a welcoming work environment that stimulates the full potential of ITRI’s members, allowing them to excel and to perform their best in application-oriented researches. We fully cultivate the capability of independent innovation through participating in international cooperation and academic programs. These collaborative activities are pursued so as to aid in the success of technological incubation and entrepreneur start-ups. We strive to strengthen the technological innovation and value creation ability for Taiwan’s industry in order to remain the competitiveness globally.

Introduction

Automated optical inspection (AOI) [1] is an automated visual inspection of printed circuit board (PCB) (or LCD,transistor) manufacture where a camera autonomously scans the device under test for both catastrophic failure (e.g. missing component) and quality defects (e.g. fillet size or shape or component skew). It is commonly used in the manufacturing process because it is a non-contact test method. It is implemented at many stages through the manufacturing process including bare board inspection, solder paste inspection (SPI), pre-reflow and post-reflow as well as other stages. The Institute of Electronics and Optoelectronics in Industrial Technology Research Institute(ITRI) has spent years on developing flexible displays, hoping to elevate the production quality with AOI technology during the pilot run. This time we have invited experts from different fields to join us, and focus on identifying defect classifications of AOI image data that are offered so as to elevate the identification efficiency of AOI through statistical science.

This is an open-ended problem that can be solved consistently over a long period of time, and has offered milestone rewards for participants. Baseline is the best score of the previous milestone, and Private Leaderboard will be updated occasionally.

Reference
[1] https://en.wikipedia.org/wiki/Automated_optical_inspection

Activity time

The milestone is set at 23:59:59 on 09/30/2019, with its Private Leaderboard being announced at 00:00:00 on 10/01/2019. The grade would be viewed as a basis for awards. Private Leaderboard will be updated occasionally before the milestone.

During the period from 6/6 to 9/30, Private Leaderboard will be updated once two weeks.

Prize Information

The final score should be uploaded before 23:59:59 on the day of milestone. The top three exceeding Baseline score (0.998521) on Private Leaderboard would be awarded as follows:


The first place: 100,000 discount points of hicloud

The second place: 100,000 discount points of hicloud

The third place: 100,000 discount points of hicloud

You will be awarded a certificate if your score outperforms Baseline on the Private Leaderboard and you pass model verification process


Rewards were provided by Chunghwa Telecom

Note:

1. Hicloud points can redeem service charge. After the discount, the price will be charged at 30% off based on the list price automatically.

2. Chunghwa Telecom deserves the right to make changes to the terms and conditions herein.

3. A model verification process will be performed to verify eligibility of awardees. Only those who pass model verification process will be awarded a certificate and/or prize.

Evaluation Criteria

After classification models of defect prediction are offered by researchers participating in the issue, the back-end of the system would process them in bathces regularly to calculate the score. Evaluations are conducted by calculating the corresponding accuracy rate of the actual value.

The following is the formula:

$$Accuracy = {\text{Number of correct predictions} \over \text{Number of total predictions}}$$

Data description

There are six categories included in image data that the issue offers (1 normal category + 5 defect categories)

The download data file (aoi_data.zip) includes:

  • train_images.zip: image data for training (PNG format), 2,528 images in total.
  • train.csv: includes 2 columns, ID and Label.
    • ID: the image filename
    • Label: defect classification category (0: normal, 1: void, 2: horizontal defect, 3: vertical defect, 4: edge defect, 5: particle)
  • test_images.zip: image data for testing (PNG format), 10,142 images in total.
  • test.csv: includes 2 columns, ID and Label.
    • ID: the image filename
    • Label: defect classification category (the value can be only one of the following numbers: 0, 1, 2, 3, 4, 5)

Upload format description

Please upload the file in CSV format, separate with commas, and save in one file. The content must correspond to number order of ID columns and include the following information.

  • ID: the image filename
  • Label: defect classification category (the value can be only one of the following numbers: 0, 1, 2, 3, 4, 5)

Rules

  • Upload limit is 5 entries per day.
  • The evaluation result would be based on the final version that you upload. If two teams (or more) got the same evaluation scores, the time they upload would determine the ranking.
  • If there is cheating or fraud during the activity, the team that cheats will be disqualified from the activity and the vacancy would be filled up by other teams in the ranking order.
  • This topic does not offer the team-up option by request of the topic provider. If there are answers identified the same during topic examination and audit, participants with identical answers would be forced to withdraw the activity, with all uploading data of the topic being eliminated.
  • Keep the personal results in a safe place, lest the data be stolen or plagiarized, leading to the impairment of individual rights.
  • Awarding: We consider an account to belong to an individual, thus the prize should be collected by only one person. Multiple winners of one award are no longer acceptable in the platform.
  • After uploading, the answers of test data would be divided into two parts to calculate the score:
    • Before the deadline of the activity: The system refers to partial Ground Truth of test data to examine and calculate the score. The result will be posted on Public Leaderboard as reference for the final score and ranking. This data accounts for 40% of the entire test data.
    • After the deadline of the activity: The system refers to Ground Truth of the remaining test data to examine and calculate the score. The result will be posted on Public Leaderboard as reference for the final score and ranking.
  • Any form of manual labeling is forbidden. A model verification process will be performed to verify eligibility of awardees. Only those who pass model verification process will be awarded a certificate and/or prize.

tcglarry2018/08/22 11:43
0

1floor

不好意思, 確定一下, 8/23 晚上之前要上傳完畢? 是嗎?
(活動到9月底為止?)

stephanie_huang2018/08/22 11:51
0

3floor

貴單位您好, 我們是自強基金會資料科學與大數據分析師養成班的學員, 對於AOI瑕疵分類的題目感到興趣, 想要更進一步讓功能性更高, 不知道可否能提供相關細節的資料? (1.為了想要更真實的test,可否透露是那種產品&產業來源? 2.含時間序列資料AOI照片) 謝謝

eric2018/08/24 16:11
0

4floor

@tcglarry 您好,我是這個議題的負責人 Eric。目前議題的活動時間已延長至 9/27,歡迎您繼續參與本議題並上傳結果!

sikadeer2018/08/29 14:49
0

5floor

既然議題的時間延長, 請問現在還可以報名參加競賽嗎?

eric2018/08/31 08:37
0

6floor

@stephanie_huang 您好,謝謝您對於「AOI瑕疵分類」議題的關注與參與。
 
對於您所提的相關細節資訊,本平台從議題提供者所取得的資料中並沒有包括這部份的資訊,所以很抱歉無法協助。
再則平台所使用的資料皆與廠商簽定保密合約,解題以外的資訊即使有恐怕也無法提供,這部份是受法律約束的,希望您能諒解。
 
平台陸續會推出一些影像相關的議題,希望您繼續給於支持並擁躍參與,感謝!

eric2018/08/31 08:39
0

7floor

@sikadeer 您好,目前活動仍在進行中,歡迎您報名參加!

sikadeer2018/08/31 10:55
0

8floor

您好, 我想報名, 可是這個議題的網頁上找不到 "我要報名" 的按鍵, 請問還有其他的方式報名嗎?

eric2018/09/03 08:26
0

9floor

@sikadeer,您好,請直接點選資料頁面中的檔案下載,簽署 NDA 後即可參加,謝謝您的參與!

tcglarry2018/09/03 22:29
0

10floor

請問
a.只分類瑕疵類別, 對實際生產有幫助嗎 ?
b. 正確率多少以上, 模型會有佈建的效益 ? 

sikadeer2018/09/14 14:05
0

11floor

已經把結果上傳了,可是Leader Board 是空空的, 我怎麼知道上傳的資料對不對? 還有沒有改善的空間? 如果過幾天又做了新的版本再上傳, 怎麼知道有沒有進步?

eric2018/09/21 13:04
0

12floor

@sikadeer 您好,在您上傳檔案之後,系統會在 Public Leaderboard 中呈現您的分數,Private Leaderboard 則會在議題活動結束之後才公佈。

eric2018/09/21 13:16
0

13floor

@tcglarry 您好,分類瑕疵類別,有助於判斷所生產的產品是否有問題,並針對不同類別做進一步的分析;至於正確率,廠商在實際評估效益時,會依照不同的產品及應用有不同的要求,謝謝!

franky2018/09/28 12:29
0

14floor

先謝謝工研院提供 AOI 資料集! 請問 10/04 會用什麼方式公佈結果? 上傳資料的人員會有機會彼此溝通交流嗎?

eric2018/10/09 13:57
0

15floor

@franky 您好,AOI 瑕疵分類議題活動已圓滿結束,結果在 10/04 已透過快訊公佈。我們目前也在籌畫社群相關功能,以供大家交流,敬請期待,謝謝!

taurus12079@gmail.com2018/10/16 12:56
0

16floor

請問能提供test_images 的正確label嗎

eric2018/10/31 11:29
0

17floor

taurus12079@gmail.com 您好,AOI議題將規劃以不同的形式持續解題,所以暫時不會將test的 label公開,敬請見諒,謝謝!

JC2018/11/08 17:30
0

18floor

@eric 這個dataset還有可能供練習使用嗎? 

eric2018/11/27 11:13
0

19floor

@JC,您好,未來會推出不同形式的解題方式,敬請期待!

aiedward2019/04/04 22:27
0

20floor

aoi.zip 無法下載,經常中斷

eric2019/04/08 09:34
0

21floor

@aiedward,您好,經測試目前可以正常下載,請再嘗試下載,謝謝!

jjftim1232019/07/25 12:13
1

29floor

請問現在還可以報名嗎?謝謝!

eric2019/07/25 13:16
1

30floor

@jjftim123,您好,請在資料頁面下載資料,簽署 NDA 之後即可參加,謝謝!

Ranking Team name Grade of Result
1 blessxu 0.9992601
2 cwhuang1021 0.9982737
3 sikadeer 0.9982737
4 stephan.kuo 0.9975339
5 sln95303 0.9970406
6 fhwang 0.9967940
7 Colmar 0.9965474
8 aiedward 0.9965474
9 tw48964896 0.9953144
10 jesse1029 0.9950678
11 LiuPiu 0.9945745
12 chengjiun.ma@gmail.com 0.9943279
13 SnorLax 0.9938347
14 teds 0.9938347
15 JackKao 0.9935881
16 Jiang 0.9935881
17 jang_jian 0.9935881
18 gn00665219 0.9933415
19 ridicon 0.9930949
20 tueswking511 0.9928483
21 hsh0703 0.9928483
22 TerrenceChou 0.9926017
23 Ted_Bear 0.9926017
24 pacude881 0.9918618
25 107378057 0.9918618
26 supertortoise 0.9918618
27 linan 0.9911220
28 Rsys 0.9911220
29 lucas85062055 0.9908754
30 inture 0.9906288
31 A610050A 0.9903822
32 PDFwithData 0.9903822
33 zolo1122 0.9901356
34 painting 0.9898890
35 johnny88850tw 0.9896424
36 chihyuu 0.9893958
37 slot9004 0.9893958
38 ab30310 0.9886559
39 franky 0.9884093
40 86oujohnny 0.9884093
41 royce 0.9881627
42 105021044 0.9879161
43 benq581 0.9876695
44 jummy1124@gmail.com 0.9876695
45 andysu840520 0.9874229
46 Colin 0.9871763
47 itri456133 0.9869297
48 J4James 0.9864364
49 kevin32111@gmail.com 0.9859432
50 ERR1121 0.9854500
51 p692584k 0.9854500
52 tommyrpg1010 0.9839704
53 chaoziyin 0.9837237
54 jamychen1126 0.9832305
55 panzer 0.9824907
56 paul369xd 0.9819975
57 Sero8139 0.9819975
58 thanhphat1221 0.9815043
59 VanSuHuynh 0.9812577
60 Allen 0.9797780
61 cheney235689 0.9797780
62 tommy860823 0.9797780
63 pups2468 0.9795314
64 mingj 0.9792848
65 taurus12079 0.9787916
66 Lucas7246 0.9782983
67 heysun0728 0.9780517
68 Wiwi 0.9778051
69 ee255852 0.9775585
70 ian06013101799 0.9775585
71 lunaseaman 0.9773119
72 flovebrs 0.9768187
73 igormorawski 0.9763255
74 chtte13 0.9760789
75 ChenJH 0.9755856
76 RayChang 0.9736128
77 electron606b 0.9733662
78 tcglarry 0.9718865
79 wayne9458 0.9709001
80 larry 0.9704069
81 y987141 0.9699136
82 katychou 0.9689272
83 YCLo 0.9689272
84 b10556037 0.9686806
85 chris880622 0.9681874
86 gash8234 0.9667077
87 redsunmirage 0.9654747
88 RogerHung 0.9639950
89 amberliu1985 0.9635018
90 edonovanto 0.9612823
91 sevillachea 0.9610357
92 socrateschch 0.9605425
93 yomingjayism 0.9600493
94 jackevin 0.9590628
95 hsin8824 0.9580764
96 sleepingpandaaa 0.9573366
97 Hsiao7033 0.9573366
98 boomdeyadah 0.9546239
99 build0220 0.9543773
100 t107598068 0.9543773
101 htchutw 0.9491985
102 aditya 0.9467324
103 Vivek 0.9467324
104 joker 0.9442663
105 geniuspingping 0.9442663
106 franco0088 0.9430332
107 ag150300 0.9408138
108 Sandra 0.9400739
109 yuanyuanjerry 0.9383477
110 jack8566662 0.9353884
111 imlm0001 0.9324290
112 chouchienu 0.9324290
113 ning364 0.9210850
114 small77 0.9119605
115 ping27942 0.9067817
116 gene3706 0.8939580
117 WindDYTING 0.8606658
118 b10556007 0.8604192
119 ainglee 0.8579531
120 siyu026019 0.8453760
121 ccccu33333 0.8268803
122 cianyu150cjo 0.8256473
123 w10041656 0.7972872
124 gcpyobcmst001 0.7819975
125 et10man 0.6912453
126 be3575 0.6848335
127 DuyDinh 0.4623921
128 pek9527 0.4545006
129 B10456005 0.3447595
130 yonglee 0.3344019
131 taurus12079@gmail.com 0.3282367
132 or624 0.2663378
133 Mingyenchu 0.2660912
134 cynthiapr 0.2547472
135 evandio 0.2199753
136 timsimtho 0.2140567
137 Felixgunawan 0.2110974
138 irfan.frans 0.2046855
For the results announcement, please refer to the event time.