Shulou(Shulou.com)06/02 Report--

This article mainly introduces "how to use github to write a lipstick number recognizer". In daily operation, I believe many people have doubts about how to use github to write a lipstick number recognizer. The editor consulted all kinds of materials and sorted out simple and easy-to-use methods of operation. I hope it will be helpful to answer the doubts of "how to use github to write a lipstick number recognizer". Next, please follow the editor to study!

Lipstick Universe from Github

To identify lipstick color numbers, you must first let the machine know what colors they have.

According to the introduction of the cabinet sister, the red color is: "Strawberry Red, Rust Red, Maple Leaf Red." and others are "bean paste, eating soil, tomato."

Does it make a difference that the world outlook begins to crumble before it is established? "the bean paste color is the most versatile, and the orange tomato color is more white." The black in front of me is not black. What kind of red do you mean?

Fortunately, in the omnipotent Github found a treasure database "lipstick color visualization", this database is comparable to the lipstick color universe, not only includes the current most mainstream brand series of color numbers, but also conscientiously arranged on the color disk.

This data set is a nested dictionary data structure in the form of a json string that records the color id, name, and hexadecimal color values of different lipstick color numbers under each lipstick brand series.

Straight! Man! Help! Star! Yes or no!

Visual link for lipstick color number:

Https://github.com/Ovilia/lipstick

However, looking at this dense color, I sincerely admire the copywriter experts of the major lipstick brands, how to distinguish each indistinguishable color, and have to take their names separately.

Foolishly, I did some statistics and color number input on the different series of five brands, so the rest was handed over to the computer.

Do an experiment with tomatoes first?

Now that there is such a complete color number database, there is a clever way to abstract bacteria: if you want to find a suitable color number, you can intercept the color directly and compare it in the database.

This method is very easy to operate, before lip color, we might as well take other red objects to practice.

For example, here is a picture of a tomato. Look at this tomato. It is big and round.

In which a rectangular picture with uniform color and no highlight is captured:

It is technically feasible to extract the RGB value of this solid color image. The getcolor.py code is as follows:

Import colorsys import PIL.Image as Image def get_dominant_color (image): max_score = 0.0001 dominant_color = None for count, in image.getcolors (image.size [0] * image.size [1]): # converted to HSV standard saturation = colorsys.rgb_to_hsv (rgamble 255.0, gmaple 255.0 Continue score 255.0) [1] y = min (abs (r*2104+g*4130+b*802+4096+131072) > > 13235) y = (ymer16.0) / (23516) # ignore the highlight color if y > 0.9: continue score = (saturation+0.1) * count if score > max_score: max_score = score dominant_color = (rmemg B) return dominant_color

In order to reduce the error, you need to cut several pictures from different locations, save them in a local folder, read the file, extract the color, calculate the average, and get the final RGB color of the tomato. The code is as follows:

Import os import getcolor from os.path import join as pjoin from scipy import misc def load_color (color_dir,list): count = 0 for dir in os.listdir (color_dir): img_dir = pjoin (color_dir Dir) image = getcolor.Image.open (img_dir) image = image.convert ('RGB') get=getcolor.get_dominant_color (image) list.append (get) count = count+1 # print (person_dir) # print (count) return count def Mean_color (count List): Mean_R=Mean_G=Mean_B=0 for i in range (count): tuple=list [I] Mean_R+=tuple [0] Mean_G+=tuple [1] Mean_B+=tuple [2] MeanC= ((int) (Mean_R/count), (int) (Mean_G/count), (int) (Mean_B/count)) return Me

The color of the tomato has been extracted, so what does it compare with?

Lipstick data, of course, Digest bacteria here used five brands, namely, Saint Laurent, Miss Chanel Coco, Dior, Maybelline, Givenchy, a total of 17 series, 271 lipstick color numbers.

The dataset is a nested dictionary data structure stored as a json string, which records the color id, name, and hexadecimal color values of different lipstick color numbers under each lipstick brand series.

Some of the datasets in lipstick.json are shown as follows:

{"brands": [{"name": "Saint Laurent", "series": [{"name": "Yingliang pure charm lipstick", "lipsticks": [{"color": "# D62352", "id": "49", "name": "flirting"}, {"color": "# DC4B41", "id": "14", "name": "falling in love at first sight"}, {"color": "# B22146", "id": "05") "name": "floating life is like a dream"}

The RGB color stored in the dataset is a hexadecimal string, which needs to be converted to a RGB value to compare whether the two colors are close or not.

In fact, it is to compare the errors in the three component dimensions of RGB, the smallest lipstick output corresponding to the brand, series, color number and id.

The code is as follows:

Import json import getcolor import numpy as np import lipcolor # filename = 'temp.txt' # # write the temp data to file## def WtoFile (filename,RGB_temp): num=len (RGB_temp) with open (filename,'w') as f: for i in range (num): s = str (RGB_ temp [I]) .replace (' [,'). Replace (']' '') f.write (s) f.write ("\ n") # operate the data # save the brand&series&color id&color name to sum_list## covert the color # D62352 to RGB_array## caculate the RGB difference to RGB_temp and write the value to file## def data_operate (): with open ('lipstick.json', 'r' Encoding='utf-8') as f: ret_dic = json.load (f) # print (ret_dic ['brands']) # print (type (ret_dic)) # # print (ret_dic [' brands'] [0] ['name']) b_num=len (ret_dic [' brands']) # print (b_num) # brands number listings = [] # series brands# for i in range (len (ret_dic ['brands']): s_num=len (ret_dic [' brands'] [I] ['series']) s_list.append (s_num) # print ("{0} has {1} series" .format (ret_dic [' brands'] [I] ['name']) (slist [I])) # the lipstick color of every brands every series# # the first loop calculate the total color numbers sum=0 for b1 in range (b_num): for S1 in range (slist [b1]): brand_name=ret_dic ['brands'] [b1] [' name'] lip_name=ret_dic ['brands'] [b1] [' Series'] [S1] ['name'] color_num=len (ret_dic [' brands'] [B1] ['series'] [S1] [' lipsticks']) sum+=color_num#calculate the total color numbers # the second loop save the message to a list# sum_list=np.zeros ((sum) 4), dtype= (str,8)) value_array=np.zeros ((sum,6) Dtype=int) item0 for b2 in range (b_num): for S2 in range (s _ list [b2]): brand_name=ret_dic ['brands'] [b2] [' name'] # print (type (brand_name)) lip_name=ret_dic ['brands'] [b2] [' series'] [S2] ['name'] Color_num=len (ret_dic ['brands'] [b2] [' series'] [S2] ['lipsticks']) for c in range (color_num): color_value=ret_dic [' brands'] [b2] ['series'] [S2] [' lipsticks'] [c] ['color'] color_name=ret_dic [' brands'] [b2] ['series'] [S2] ['lipsticks'] [c] [' name'] color_id=ret_dic ['brands'] [b2] [' series'] [S2] ['lipsticks'] [c] [' id'] # print ("{0} series {1} has {2} colors Color {3}: {4} ".format (brand_name,lip_name,color_num,c+1 Color_name) sum_ list [I] [0] = brand_name sum_ list [I] [1] = lip_name sum_ list [I] [2] = color_id sum_ list [I] [3] = color_name # value_ array [I] = value_ array [I] [1] # convert "# D62352" to [13 62352] # for l in range (6): temp=color_ value [l + 1] if (temp > = 'A'and temp

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.