Week11_1Application Photo OCR

Week11_1Application Photo OCR

第 1 題

Suppose you are running a sliding window detector to find text in images.
Your input images are 1000x1000 pixels. You will run your sliding windows detector at two scales,
10x10 and 20x20 (i.e., you will run your classifier on lots of 10x10 patches to decide if they contain text or not;
and also on lots of 20x20 patches), and you will “step” your detector by 2 pixels each time.
About how many times will you end up running your classifier on a single 1000x1000 test set image?

• 500,000
• 1,000,000
• 100,000
• 250,000
  *     答案: 1 *
  * 解析: 用滑動窗口去檢測圖像中的文字, 窗口大小是(10x10)或(20x20)一次滑動2個像素 *
  * 每個窗口滑動的次數是: (1000x1000)/(2x2)=250,000 因爲有兩個窗口, 所以需要再乘以2 *

---

第 2 題

Suppose that you just joined a product team that has been developing a machine learning application, using training examples.
You discover that you have the option of hiring additional personnel to help collect and label data.
You estimate that you would have to pay each of the labellers $10 per hour,
and that each labeller can label 4 examples per minute.
About how much will it cost to hire labellers to label 10,000 new training examples?

• $400
• $600
• $250
• $10,000

*     答案: 1 *
解析: 1分鐘4個lable, 則1小時4x60=240個lable,10,000個lable, 需要10000/240=41.66小時
1小時$10,則42小時花$420, 答案中只有$400最接近

---

第 3 題

What are the benefits of performing a ceiling analysis? Check all that apply.

• It is a way of providing additional training data to the algorithm.
• It helps us decide on allocation of resources in terms of which component in a machine learning pipeline to spend more effort on.
• It can help indicate that certain components of a system might not be worth a significant amount of work improving,
  because even if it had perfect performance its impact on the overall system may be small.
• If we have a low-performing component, the ceiling analysis can tell us if that component has a high bias problem or a high variance problem.

*     答案: 2 3 *
* 選項1: 使用上限分析並沒有增加訓練樣本. 不正確 *
* 選項2: 使用上限分析能幫助我們分析流水線的哪個部分對整個系統的提高最大. 正確 *
* 選項3: 使用上限分析能讓我們知道到某個模塊需不需要花精力做好;因爲就算把這個模塊精度提高到100%了,也無助於提高整個系統的精度. 正確 *
* 選項4: 使用上限分析並不會幫我們分析出哪個部分是high bias,哪個部分是high variance. 不正確 *

---

第 4 題

Suppose you are building an object classifier, that takes as input an image,
and recognizes that image as either containing a car (y=1$y=1$ ) or not (y=0$y=0$ ).
For example, here are a positive example and a negative example:

After carefully analyzing the performance of your algorithm,
you conclude that you need more positive (y=1$y=1$ ) training examples.
Which of the following might be a good way to get additional positive examples?

• Apply translations, distortions, and rotations to the images already in your training set.
• Select two car images and average them to make a third example.
• Take a few images from your training set, and add random, gaussian noise to every pixel.
• Make two copies of each image in the training set; this immediately doubles your training set size.

*     答案: 1 *
* 你做了一個物體檢測程序,識別圖像中有沒有car. 經過認真檢查,你需要更多的訓練樣本. 下面哪一個方法是增加正確樣本的途徑 *
* 選項1: 對己有的訓練樣本進行一些增加變形 扭曲 旋轉的處理,生成新的訓練樣本. 手動創造大量的樣本. 正確 *

---

第 5 題

Suppose you have a PhotoOCR system, where you have the following pipeline:

You have decided to perform a ceiling analysis on this system, and find the following:

Which of the following statements are true?

• There is a large gain in performance possible in improving the character recognition system.
• Performing the ceiling analysis shown here requires that we have ground-truth labels for the text detection, character segmentation and the character recognition systems.
• The least promising component to work on is the character recognition system, since it is already obtaining 100% accuracy.
• The most promising component to work on is the text detection system, since it has the lowest performance (72%) and thus the biggest potential gain.

*     答案: 1 2 *
* 解析: 你做了一個圖像中文字識別系統, 經過pipline的四步進行處理. 然後做了一個ceiling analysis分析: *
* Text detection 對整個系統有2%的提升 *
* Character segmentation 對整個系統有10%的提升 *
* Character recognition 對整個系統有18%的提升 *
* 選項1: 當提高Character recognition時會對整個文字識別系統有較大的提升. 正確 *
* 選項2: 要用這兒提到的上限分析(ceiling analysis),需要我們對其它的三個流程都加上標籤來判斷對錯(ground-truth). 正確 *
* 選項3: Character recognition 會有18%的提升. 不正確 *
* 選項4: Text detection 會有2%的提升. 不正確 *