次のページの出力を、日本語にしました。
Python の requests で、Watoson の画像認識を使う

実行したときの様子

get_url_visual.py

# ! /usr/bin/python
# -*- coding: utf-8 -*-
#
#	get_url_visual.py
#
#					Sep/06/2017
#
# --------------------------------------------------------------------
import sys
import json
import requests
#
# --------------------------------------------------------------------
def get_url_visual_proc(url_jpg):
	api_key="31b9172e4832c2339dc9e6d2e89cfadc5110692"
	version="2016-05-20"
#
	payload = {
		'api_key': api_key,
		'version': version,
		'url': url_jpg,
		'owners': 'IBM',
		'classifier_ids': 'default'
		}

	headers = {
		'Accept': 'application/json',
		'Accept-Language': 'ja'
		}

	url_api = "https://gateway-a.watsonplatform.net/visual-recognition/api/v3/classify"
	rr = requests.get(url_api,params=payload,headers=headers)
#
	print(rr)
	print()
#	print(rr.text)
#	print()
	dict_aa=json.loads(rr.text)
#
	rvalue = []
	for it in range(3):
		unit=dict_aa["images"][0]["classifiers"][0]["classes"][it]
		rvalue.append(unit)
#
	return rvalue
#
# --------------------------------------------------------------------
sys.stderr.write("*** 開始 ***\n")
#
url_jpg="https://github.com/watson-developer-cloud/doc-tutorial-downloads/raw/master/visual-recognition/fruitbowl.jpg"
#
rvalue=get_url_visual_proc(url_jpg)
#
for unit in rvalue:
	print (unit["class"],unit["score"])
#
sys.stderr.write("*** 終了 ***\n")
# --------------------------------------------------------------------